{ "schema_version": "1.0.0", "generated_at": "2026-08-30T20:57:49.819Z", "site": "https://pyweb.dev", "stats": { "total_nodes": 190, "total_edges": 680, "wiki_pages": 181, "writing_posts": 9 }, "nodes": [ { "id": "wiki:ag-ui-protocol", "slug": "ag-ui-protocol", "title": "AG-UI Protocol", "section": "concepts", "type": "concept", "description": "Open, lightweight, event-based standard connecting AI agent runtimes to user-facing frontend applications.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "agents", "workflow", "context-engineering", "subagents" ], "sources": [], "url": "https://pyweb.dev/wiki/ag-ui-protocol", "raw_markdown_url": "https://pyweb.dev/wiki/ag-ui-protocol.md" }, { "id": "wiki:agent-containment-and-blast-radius", "slug": "agent-containment-and-blast-radius", "title": "Agent Containment and Blast Radius", "section": "concepts", "type": "concept", "description": "Capping what an agent can do — not just what it tends to do — via sandboxes, VMs, egress controls, and classifier-gated approvals layered over fallible human oversight.", "created": "2026-08-24", "updated": "2026-08-29", "tags": [ "agents", "security", "workflow", "evaluation" ], "sources": [ "raw/articles/anthropic-engineering-how-we-contain-claude-2026.md", "raw/articles/anthropic-engineering-claude-code-auto-mode-2026.md", "raw/articles/simon-willison-breaking-claude-code-opus-5-auto-mode-2026.md" ], "url": "https://pyweb.dev/wiki/agent-containment-and-blast-radius", "raw_markdown_url": "https://pyweb.dev/wiki/agent-containment-and-blast-radius.md" }, { "id": "wiki:agent-harness-engineering", "slug": "agent-harness-engineering", "title": "Agent Harness Engineering", "section": "concepts", "type": "concept", "description": "Designing the runtime infrastructure around an agent's model — sandboxes, tool contracts, progressive disclosure, and verification gates — as the primary driver of reliability.", "created": "2026-08-24", "updated": "2026-08-30", "tags": [ "agents", "context-engineering", "subagents", "workflow", "evaluation" ], "sources": [], "url": "https://pyweb.dev/wiki/agent-harness-engineering", "raw_markdown_url": "https://pyweb.dev/wiki/agent-harness-engineering.md" }, { "id": "wiki:agent-native-infrastructure", "slug": "agent-native-infrastructure", "title": "Agent-Native Infrastructure", "section": "concepts", "type": "concept", "description": "Full-stack platforms designed around machine cognition, deterministic state machines, and cryptographic agent identity rather than human developer tools.", "created": "2026-08-23", "updated": "2026-08-30", "tags": [ "agents", "context-engineering", "subagents", "knowledge-management", "workflow" ], "sources": [], "url": "https://pyweb.dev/wiki/agent-native-infrastructure", "raw_markdown_url": "https://pyweb.dev/wiki/agent-native-infrastructure.md" }, { "id": "wiki:agentic-code-quality", "slug": "agentic-code-quality", "title": "Agentic Code Quality", "section": "concepts", "type": "concept", "description": "Risk-conditioned verification and authorization controls for autonomous software development.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "coding-guidelines", "feedback-loops", "tdd", "workflow", "evaluation", "security" ], "sources": [], "url": "https://pyweb.dev/wiki/agentic-code-quality", "raw_markdown_url": "https://pyweb.dev/wiki/agentic-code-quality.md" }, { "id": "wiki:agentic-engineering-patterns", "slug": "agentic-engineering-patterns", "title": "Agentic Engineering Patterns", "section": "concepts", "type": "concept", "description": "Disciplined software engineering practices for working with autonomous coding agents that write, test, and verify code in loops.", "created": "2026-08-22", "updated": "2026-08-27", "tags": [ "agents", "workflow", "principle", "coding-guidelines", "tdd" ], "sources": [], "url": "https://pyweb.dev/wiki/agentic-engineering-patterns", "raw_markdown_url": "https://pyweb.dev/wiki/agentic-engineering-patterns.md" }, { "id": "wiki:agentic-manual-testing", "slug": "agentic-manual-testing", "title": "Agentic Manual Testing", "section": "concepts", "type": "concept", "description": "Directing coding agents to actively exercise running servers, APIs, CLI one-liners, and browser automation to verify real system behaviour.", "created": "2026-08-22", "updated": "2026-08-22", "tags": [ "technique", "agents", "feedback-loops", "workflow" ], "sources": [ "raw/articles/simon-willison-agentic-manual-testing-2026.md", "raw/articles/simon-willison-first-run-the-tests-2026.md" ], "url": "https://pyweb.dev/wiki/agentic-manual-testing", "raw_markdown_url": "https://pyweb.dev/wiki/agentic-manual-testing.md" }, { "id": "wiki:agentic-software-factory", "slug": "agentic-software-factory", "title": "Agentic Software Factory", "section": "concepts", "type": "concept", "description": "Operating model for software development where autonomous AI agents perform end-to-end delivery under harness constraints and risk-tiered human oversight.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "workflow", "agents", "coding-guidelines", "subagents" ], "sources": [ "raw/articles/augment-code-software-factory-vs-devops-2026.md", "raw/articles/hugo-bowne-anderson-agentic-software-factory-2026.md", "raw/articles/addy-osmani-agentic-code-quality-2026.md" ], "url": "https://pyweb.dev/wiki/agentic-software-factory", "raw_markdown_url": "https://pyweb.dev/wiki/agentic-software-factory.md" }, { "id": "wiki:agentic-vulnerability-lifecycle", "slug": "agentic-vulnerability-lifecycle", "title": "Agentic Vulnerability Lifecycle", "section": "concepts", "type": "concept", "description": "The collapse of traditional security embargo windows and CVE disclosure pipelines driven by automated coding agents that synthesize working exploits within minutes of patch discussions.", "created": "2026-08-29", "updated": "2026-08-29", "tags": [ "security", "agents", "workflow", "anti-patterns" ], "sources": [], "url": "https://pyweb.dev/wiki/agentic-vulnerability-lifecycle", "raw_markdown_url": "https://pyweb.dev/wiki/agentic-vulnerability-lifecycle.md" }, { "id": "wiki:agents-md-spec", "slug": "agents-md-spec", "title": "AGENTS.md Specification", "section": "concepts", "type": "concept", "description": "The root project context standard for orienting AI coding agents without system prompt bloat.", "created": "2026-08-22", "updated": "2026-08-27", "tags": [ "agents", "context-engineering", "skills", "workflow" ], "sources": [ "raw/articles/aihero-dev-homepage-2026.md", "raw/articles/agentic-engineering-trends-2026-synthesis.md", "raw/articles/aihero-ai-coding-dictionary-2026.md" ], "url": "https://pyweb.dev/wiki/agents-md-spec", "raw_markdown_url": "https://pyweb.dev/wiki/agents-md-spec.md" }, { "id": "wiki:agents-vs-workflows", "slug": "agents-vs-workflows", "title": "Agents vs Workflows", "section": "concepts", "type": "concept", "description": "The degree-of-autonomy spectrum from Anthropic's Building Effective Agents: workflows run on developer-defined code paths, agents direct their own process via tools and environment feedback.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "agents", "patterns", "llm-fundamentals" ], "sources": [ "raw/aihero/building-effective-agents.md", "raw/aihero/what-is-an-agent.md", "raw/aihero/what-is-an-ai-engineer.md" ], "url": "https://pyweb.dev/wiki/agents-vs-workflows", "raw_markdown_url": "https://pyweb.dev/wiki/agents-vs-workflows.md" }, { "id": "wiki:ai-coding-taxonomy", "slug": "ai-coding-taxonomy", "title": "AI Coding Taxonomy & Agent Experience", "section": "concepts", "type": "concept", "description": "Core vocabulary and operational taxonomy for AI coding agents, attention dynamics, developer/agent experience (DX/AX), and execution modes.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "agents", "context-engineering", "coding-guidelines", "workflow", "principle" ], "sources": [ "raw/articles/aihero-ai-coding-dictionary-2026.md" ], "url": "https://pyweb.dev/wiki/ai-coding-taxonomy", "raw_markdown_url": "https://pyweb.dev/wiki/ai-coding-taxonomy.md" }, { "id": "wiki:ai-engineer-role", "slug": "ai-engineer-role", "title": "AI Engineer Role", "section": "concepts", "type": "concept", "description": "The application-layer engineer who orchestrates AI APIs, RAG, and evals — distinct from ML Engineering by the API boundary, grounded in Latent Space's 'Rise of the AI Engineer'.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "llm-fundamentals", "workflow", "roles" ], "sources": [ "raw/aihero/what-is-an-ai-engineer.md", "raw/aihero/the-ai-engineer-mindset.md", "raw/aihero/ai-engineer-roadmap.md", "raw/aihero/what-are-llms-used-for.md" ], "url": "https://pyweb.dev/wiki/ai-engineer-role", "raw_markdown_url": "https://pyweb.dev/wiki/ai-engineer-role.md" }, { "id": "wiki:automated-eval-engineering", "slug": "automated-eval-engineering", "title": "Automated Eval Engineering", "section": "concepts", "type": "concept", "description": "Techniques and harnesses for constructing reproducible, containerized agent evaluations from repository code and production traces.", "created": "2026-08-22", "updated": "2026-08-22", "tags": [ "evaluation", "agents", "workflow", "feedback-loops" ], "sources": [ "raw/articles/langchain-automating-eval-engineering-2026.md", "raw/articles/parlance-labs-do-automated-evals-work-2026.md" ], "url": "https://pyweb.dev/wiki/automated-eval-engineering", "raw_markdown_url": "https://pyweb.dev/wiki/automated-eval-engineering.md" }, { "id": "wiki:build-from-scratch-pedagogy", "slug": "build-from-scratch-pedagogy", "title": "Build-From-Scratch Pedagogy", "section": "concepts", "type": "concept", "description": "Building the minimal toy version from scratch as the primary mechanism for deep understanding.", "created": "2026-08-22", "updated": "2026-08-24", "tags": [ "pedagogy", "technique", "agents" ], "sources": [ "raw/articles/karpathy-guidelines-skill-2026.md", "raw/articles/aihero-dev-homepage-2026.md" ], "url": "https://pyweb.dev/wiki/build-from-scratch-pedagogy", "raw_markdown_url": "https://pyweb.dev/wiki/build-from-scratch-pedagogy.md" }, { "id": "wiki:claude-managed-agents", "slug": "claude-managed-agents", "title": "Claude Managed Agents", "section": "concepts", "type": "concept", "description": "Anthropic's cloud-hosted agent runtime platform decoupling reasoning loops from containerized sandbox execution.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "agents", "context-engineering", "workflow", "security" ], "sources": [], "url": "https://pyweb.dev/wiki/claude-managed-agents", "raw_markdown_url": "https://pyweb.dev/wiki/claude-managed-agents.md" }, { "id": "wiki:clean-architecture", "slug": "clean-architecture", "title": "Clean Architecture", "section": "concepts", "type": "concept", "description": "Uncle Bobs dependency-inward organizing rule applied to agent systems: source dependencies point toward stable abstractions.", "created": "2026-08-25", "updated": "2026-08-30", "tags": [ "principle", "workflow" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/clean-architecture", "raw_markdown_url": "https://pyweb.dev/wiki/clean-architecture.md" }, { "id": "wiki:closed-loop-agent-improvement", "slug": "closed-loop-agent-improvement", "title": "Closed-Loop Agent Improvement", "section": "concepts", "type": "concept", "description": "End-to-end telemetry and verification architecture where production failure traces drive automated candidate PR generation and benchmark gating.", "created": "2026-08-22", "updated": "2026-08-22", "tags": [ "agents", "feedback-loops", "workflow", "evaluation" ], "sources": [ "raw/articles/replit-evaluating-and-improving-agent-at-scale-2026.md", "raw/articles/hamel-ai-product-engineering-notes-2026.md" ], "url": "https://pyweb.dev/wiki/closed-loop-agent-improvement", "raw_markdown_url": "https://pyweb.dev/wiki/closed-loop-agent-improvement.md" }, { "id": "wiki:codex-harness-architecture", "slug": "codex-harness-architecture", "title": "Codex Harness Architecture", "section": "concepts", "type": "concept", "description": "Architecture of OpenAI's Codex harness: Clean/Hexagonal design, JSON-RPC app-server decoupling, multi-platform sandboxing, and bounded execution.", "created": "2026-08-27", "updated": "2026-08-30", "tags": [ "agents", "context-engineering", "security", "workflow", "coding-guidelines" ], "sources": [], "url": "https://pyweb.dev/wiki/codex-harness-architecture", "raw_markdown_url": "https://pyweb.dev/wiki/codex-harness-architecture.md" }, { "id": "wiki:cognitive-debt-and-walkthroughs", "slug": "cognitive-debt-and-walkthroughs", "title": "Cognitive Debt and Walkthroughs", "section": "concepts", "type": "concept", "description": "Techniques for understanding agent-generated code through structured linear walkthroughs and interactive explanations to prevent cognitive debt.", "created": "2026-08-22", "updated": "2026-08-22", "tags": [ "pedagogy", "technique", "agents", "knowledge-management" ], "sources": [ "raw/articles/simon-willison-linear-walkthroughs-2026.md", "raw/articles/simon-willison-interactive-explanations-2026.md" ], "url": "https://pyweb.dev/wiki/cognitive-debt-and-walkthroughs", "raw_markdown_url": "https://pyweb.dev/wiki/cognitive-debt-and-walkthroughs.md" }, { "id": "wiki:conformance-suites-as-fitness-functions", "slug": "conformance-suites-as-fitness-functions", "title": "Conformance Suites as Fitness Functions", "section": "concepts", "type": "concept", "description": "Pairing agents with uncompromising deterministic test suites so they act as autonomous optimization engines instead of drifting generators.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "agents", "evaluation", "tdd", "workflow", "principle" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md" ], "url": "https://pyweb.dev/wiki/conformance-suites-as-fitness-functions", "raw_markdown_url": "https://pyweb.dev/wiki/conformance-suites-as-fitness-functions.md" }, { "id": "wiki:constraint-layering", "slug": "constraint-layering", "title": "Constraint Layering", "section": "concepts", "type": "concept", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "agentic-patterns", "harness-engineering", "security" ], "sources": [ "raw/articles/agentic-engineering-systems-evidence-report-2026.md", "raw/articles/addy-osmani-agent-skills-2026.md", "raw/articles/anthropic-agent-skills-2025.md" ], "url": "https://pyweb.dev/wiki/constraint-layering", "raw_markdown_url": "https://pyweb.dev/wiki/constraint-layering.md" }, { "id": "wiki:context-budget-audit", "slug": "context-budget-audit", "title": "Context Budget Audit", "section": "concepts", "type": "concept", "description": "Measuring and cutting per-turn token overhead — /context, logging proxies, disable flags, and deny rules to kill harness bloat.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "context-engineering", "agents", "cost" ], "sources": [ "raw/aihero/how-to-kill-the-bloat-in-claude-codes-system-prompt.md", "raw/aihero/essential-ai-coding-feedback-loops-for-type-script-projects.md", "raw/aihero/how-to-use-claude-code-hooks-to-enforce-the-right-cli.md", "raw/aihero/never-run-claude-init.md" ], "url": "https://pyweb.dev/wiki/context-budget-audit", "raw_markdown_url": "https://pyweb.dev/wiki/context-budget-audit.md" }, { "id": "wiki:context-engineering", "slug": "context-engineering", "title": "Context Engineering", "section": "concepts", "type": "concept", "description": "Curating high-signal context (AGENTS.md, CONTEXT.md, ADRs) to maximize agent reasoning performance.", "created": "2026-08-22", "updated": "2026-08-24", "tags": [ "agents", "context-engineering", "workflow" ], "sources": [ "raw/articles/aihero-dev-homepage-2026.md", "raw/articles/mattpocock-skills-repo-2026.md" ], "url": "https://pyweb.dev/wiki/context-engineering", "raw_markdown_url": "https://pyweb.dev/wiki/context-engineering.md" }, { "id": "wiki:context-rot", "slug": "context-rot", "title": "Context Rot", "section": "concepts", "type": "concept", "description": "The progressive degradation of LLM reasoning performance as context length and irrelevant tokens accumulate.", "created": "2026-08-22", "updated": "2026-08-30", "tags": [ "agents", "context-engineering", "anti-patterns" ], "sources": [ "raw/articles/aihero-dev-homepage-2026.md", "raw/articles/agentic-engineering-trends-2026-synthesis.md", "raw/articles/aihero-ai-coding-dictionary-2026.md" ], "url": "https://pyweb.dev/wiki/context-rot", "raw_markdown_url": "https://pyweb.dev/wiki/context-rot.md" }, { "id": "wiki:cordis-framework", "slug": "cordis-framework", "title": "Cordis Framework", "section": "concepts", "type": "concept", "description": "Microkernel plugin and dependency-injection framework powering DeepSeek Harness: lifecycle management, service containers, typed event buses, reversible side-effects.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "agents", "workflow", "principle" ], "sources": [], "url": "https://pyweb.dev/wiki/cordis-framework", "raw_markdown_url": "https://pyweb.dev/wiki/cordis-framework.md" }, { "id": "wiki:deepseek-harness", "slug": "deepseek-harness", "title": "DeepSeek Harness", "section": "concepts", "type": "concept", "description": "DeepSeek's open-source agent runtime built on the Agent = Model + Harness thesis: modular, traceable execution without hardcoded core logic.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "agents", "context-engineering", "subagents", "workflow", "evaluation" ], "sources": [], "url": "https://pyweb.dev/wiki/deepseek-harness", "raw_markdown_url": "https://pyweb.dev/wiki/deepseek-harness.md" }, { "id": "wiki:dependency-inversion-principle", "slug": "dependency-inversion-principle", "title": "Dependency Inversion Principle", "section": "concepts", "type": "concept", "description": null, "created": "2026-08-25", "updated": "2026-08-25", "tags": [ "principle" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/dependency-inversion-principle", "raw_markdown_url": "https://pyweb.dev/wiki/dependency-inversion-principle.md" }, { "id": "wiki:dependency-rule", "slug": "dependency-rule", "title": "Dependency Rule", "section": "concepts", "type": "concept", "description": null, "created": "2026-08-25", "updated": "2026-08-25", "tags": [ "principle" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/dependency-rule", "raw_markdown_url": "https://pyweb.dev/wiki/dependency-rule.md" }, { "id": "wiki:designing-for-verifiability", "slug": "designing-for-verifiability", "title": "Designing for Verifiability", "section": "concepts", "type": "concept", "description": "'It's hard to eval' is a product smell — artifacts hard for you to verify are hard for users too; design checkable artifacts before building evals.", "created": "2026-08-24", "updated": "2026-08-30", "tags": [ "evaluation", "workflow", "feedback-loops", "principle" ], "sources": [ "raw/articles/hamel-husain-it-s-hard-to-eval-is-a-product-smell-2026.md" ], "url": "https://pyweb.dev/wiki/designing-for-verifiability", "raw_markdown_url": "https://pyweb.dev/wiki/designing-for-verifiability.md" }, { "id": "wiki:deterministic-lint-gates", "slug": "deterministic-lint-gates", "title": "Deterministic Lint Gates", "section": "concepts", "type": "concept", "description": "Rust-speed linters with error-only configs as the Tier 1 mechanical backpressure layer for agentic coding loops.", "created": "2026-08-28", "updated": "2026-08-30", "tags": [ "coding-guidelines", "feedback-loops", "agents", "workflow" ], "sources": [], "url": "https://pyweb.dev/wiki/deterministic-lint-gates", "raw_markdown_url": "https://pyweb.dev/wiki/deterministic-lint-gates.md" }, { "id": "wiki:editorial-diagrams-and-visual-explanations", "slug": "editorial-diagrams-and-visual-explanations", "title": "Editorial Diagrams and Visual Explanations", "section": "concepts", "type": "concept", "description": "Design principles, semantic patterns, and standards for generating high-signal, self-contained visual diagrams in agentic workflows.", "created": "2026-08-23", "updated": "2026-08-23", "tags": [ "diagrams", "visual-explanation", "agents", "technique", "pedagogy" ], "sources": [ "raw/articles/cathryn-lavery-diagram-design-2026.md" ], "url": "https://pyweb.dev/wiki/editorial-diagrams-and-visual-explanations", "raw_markdown_url": "https://pyweb.dev/wiki/editorial-diagrams-and-visual-explanations.md" }, { "id": "wiki:error-analysis-and-evals", "slug": "error-analysis-and-evals", "title": "Error Analysis and Evals", "section": "concepts", "type": "concept", "description": "Qualitative inspection of production traces to discover failure modes, build domain-specific taxonomies, and derive trustworthy evaluation rubrics.", "created": "2026-08-22", "updated": "2026-08-30", "tags": [ "evaluation", "workflow", "feedback-loops", "context-engineering" ], "sources": [ "raw/articles/parlance-labs-do-automated-evals-work-2026.md", "raw/articles/hamel-ai-product-engineering-notes-2026.md", "raw/articles/hamel-husain-the-revenge-of-the-data-scientist-2026.md" ], "url": "https://pyweb.dev/wiki/error-analysis-and-evals", "raw_markdown_url": "https://pyweb.dev/wiki/error-analysis-and-evals.md" }, { "id": "wiki:eval-driven-development", "slug": "eval-driven-development", "title": "Eval-Driven Development", "section": "concepts", "type": "concept", "description": "Iterative, trace-grounded engineering discipline for discovering, encoding, and continuously testing GenAI failure modes.", "created": "2026-08-27", "updated": "2026-08-30", "tags": [ "evaluation", "feedback-loops", "coding-guidelines", "workflow" ], "sources": [], "url": "https://pyweb.dev/wiki/eval-driven-development", "raw_markdown_url": "https://pyweb.dev/wiki/eval-driven-development.md" }, { "id": "wiki:eval-taxonomy", "slug": "eval-taxonomy", "title": "Eval Taxonomy", "section": "concepts", "type": "concept", "description": "Evals as the AI engineer's unit tests: deterministic pass/fail checks, LLM-as-judge smoke tests, and human feedback — three tiers for wrangling predictability from probabilistic systems.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "evaluation", "llm-fundamentals", "quality" ], "sources": [ "raw/aihero/what-are-evals.md", "raw/aihero/three-types-of-evals.md", "raw/aihero/evalite-v1-preview.md", "raw/aihero/the-ai-engineer-mindset.md" ], "url": "https://pyweb.dev/wiki/eval-taxonomy", "raw_markdown_url": "https://pyweb.dev/wiki/eval-taxonomy.md" }, { "id": "wiki:evals-skills", "slug": "evals-skills", "title": "Evals Skills", "section": "concepts", "type": "concept", "description": null, "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "evaluation", "skills", "agents", "workflow" ], "sources": [ "raw/articles/hamel-husain-evals-skills-for-coding-agents-2026.md" ], "url": "https://pyweb.dev/wiki/evals-skills", "raw_markdown_url": "https://pyweb.dev/wiki/evals-skills.md" }, { "id": "wiki:feynman-technique", "slug": "feynman-technique", "title": "The Feynman Technique", "section": "concepts", "type": "concept", "description": "Teaching and learning methodology: plain English explanations, identifying gaps, and radical simplification.", "created": "2026-08-22", "updated": "2026-08-24", "tags": [ "technique", "teaching", "pedagogy" ], "sources": [ "raw/articles/aihero-dev-homepage-2026.md", "raw/articles/karpathy-guidelines-skill-2026.md" ], "url": "https://pyweb.dev/wiki/feynman-technique", "raw_markdown_url": "https://pyweb.dev/wiki/feynman-technique.md" }, { "id": "wiki:first-principles-thinking", "slug": "first-principles-thinking", "title": "First-Principles Thinking", "section": "concepts", "type": "concept", "description": "Stripping complex problems to fundamental verifiable truths and rebuilding solutions upward.", "created": "2026-08-22", "updated": "2026-08-24", "tags": [ "principle", "worldview", "technique" ], "sources": [ "raw/articles/aihero-dev-homepage-2026.md", "raw/articles/karpathy-guidelines-skill-2026.md" ], "url": "https://pyweb.dev/wiki/first-principles-thinking", "raw_markdown_url": "https://pyweb.dev/wiki/first-principles-thinking.md" }, { "id": "wiki:five-debts-of-agentic-engineering", "slug": "five-debts-of-agentic-engineering", "title": "Five Debts of Agentic Engineering", "section": "concepts", "type": "concept", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "agentic-patterns", "code-quality", "architecture", "workflow" ], "sources": [ "raw/articles/agentic-engineering-systems-evidence-report-2026.md", "raw/articles/addy-osmani-agent-skills-2026.md", "raw/articles/mattpocock-skills-repo-2026.md" ], "url": "https://pyweb.dev/wiki/five-debts-of-agentic-engineering", "raw_markdown_url": "https://pyweb.dev/wiki/five-debts-of-agentic-engineering.md" }, { "id": "wiki:generator-evaluator-loop", "slug": "generator-evaluator-loop", "title": "Generator-Evaluator Loop", "section": "concepts", "type": "concept", "description": "Generate then adversarially evaluate: a proposal loop where a separate evaluator checks each output against explicit criteria.", "created": "2026-08-24", "updated": "2026-08-30", "tags": [ "agents", "evaluation", "feedback-loops", "subagents", "workflow" ], "sources": [ "raw/articles/anthropic-engineering-harness-design-long-running-apps-2026.md", "raw/articles/anthropic-demystifying-evals-for-ai-agents-2026.md" ], "url": "https://pyweb.dev/wiki/generator-evaluator-loop", "raw_markdown_url": "https://pyweb.dev/wiki/generator-evaluator-loop.md" }, { "id": "wiki:git-for-agentic-workflows", "slug": "git-for-agentic-workflows", "title": "Git for Agentic Workflows", "section": "concepts", "type": "concept", "description": "Leveraging coding agents' native git fluency to explore repo history, resolve complex merge conflicts, bisect bugs, and rewrite clean commit stories.", "created": "2026-08-22", "updated": "2026-08-22", "tags": [ "git", "workflow", "agents", "technique" ], "sources": [ "raw/articles/simon-willison-using-git-with-coding-agents-2026.md", "raw/articles/simon-willison-anti-patterns-2026.md" ], "url": "https://pyweb.dev/wiki/git-for-agentic-workflows", "raw_markdown_url": "https://pyweb.dev/wiki/git-for-agentic-workflows.md" }, { "id": "wiki:grill-with-docs", "slug": "grill-with-docs", "title": "Grill With Docs", "section": "concepts", "type": "concept", "description": "Stateful interactive alignment skill that captures domain vocabulary into CONTEXT.md and three-gated decisions into ADRs.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "workflow", "agents", "context-engineering", "skills" ], "sources": [ "raw/articles/aihero-skills-grill-with-docs-2026.md", "raw/articles/aihero-ai-coding-dictionary-2026.md", "raw/articles/aihero-dev-homepage-2026.md" ], "url": "https://pyweb.dev/wiki/grill-with-docs", "raw_markdown_url": "https://pyweb.dev/wiki/grill-with-docs.md" }, { "id": "wiki:grilling-doctrine", "slug": "grilling-doctrine", "title": "Grilling Doctrine", "section": "concepts", "type": "concept", "description": "Relentless adversarial interview methodology to sharpen architecture and surface assumptions before coding.", "created": "2026-08-22", "updated": "2026-08-30", "tags": [ "workflow", "agents", "principle" ], "sources": [ "raw/articles/matt-pocock-interviews-2023.md", "raw/articles/aihero-dev-homepage-2026.md" ], "url": "https://pyweb.dev/wiki/grilling-doctrine", "raw_markdown_url": "https://pyweb.dev/wiki/grilling-doctrine.md" }, { "id": "wiki:handoff-artifacts", "slug": "handoff-artifacts", "title": "Handoff Artifacts", "section": "concepts", "type": "concept", "description": "Structured, self-contained markdown documents that bridge context across session boundaries and multi-agent workflows.", "created": "2026-08-22", "updated": "2026-08-27", "tags": [ "agents", "context-engineering", "workflow" ], "sources": [ "raw/articles/aihero-dev-homepage-2026.md", "raw/articles/mattpocock-skills-repo-2026.md", "raw/articles/aihero-ai-coding-dictionary-2026.md" ], "url": "https://pyweb.dev/wiki/handoff-artifacts", "raw_markdown_url": "https://pyweb.dev/wiki/handoff-artifacts.md" }, { "id": "wiki:hexagonal-architecture", "slug": "hexagonal-architecture", "title": "Hexagonal Architecture", "section": "concepts", "type": "concept", "description": null, "created": "2026-08-25", "updated": "2026-08-25", "tags": [ "principle", "workflow" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/hexagonal-architecture", "raw_markdown_url": "https://pyweb.dev/wiki/hexagonal-architecture.md" }, { "id": "wiki:hoard-and-recombine", "slug": "hoard-and-recombine", "title": "Hoard and Recombine", "section": "concepts", "type": "concept", "description": "Collecting verified working code snippets and proof-of-concept tools to supply as concrete reference material for coding agents.", "created": "2026-08-22", "updated": "2026-08-30", "tags": [ "technique", "agents", "knowledge-management", "workflow" ], "sources": [ "raw/articles/simon-willison-hoard-things-you-know-how-to-do-2026.md", "raw/articles/simon-willison-adding-a-new-content-type-2026.md" ], "url": "https://pyweb.dev/wiki/hoard-and-recombine", "raw_markdown_url": "https://pyweb.dev/wiki/hoard-and-recombine.md" }, { "id": "wiki:idea-to-ship-flow", "slug": "idea-to-ship-flow", "title": "Idea-to-Ship Flow", "section": "concepts", "type": "concept", "description": "End-to-end disciplined engineering workflow moving from grilled ideas to specs, tickets, and verified PRs.", "created": "2026-08-22", "updated": "2026-08-24", "tags": [ "workflow", "agents", "principle" ], "sources": [ "raw/articles/aihero-dev-homepage-2026.md", "raw/articles/mattpocock-skills-repo-2026.md" ], "url": "https://pyweb.dev/wiki/idea-to-ship-flow", "raw_markdown_url": "https://pyweb.dev/wiki/idea-to-ship-flow.md" }, { "id": "wiki:karpathy-four-guidelines", "slug": "karpathy-four-guidelines", "title": "Karpathy's Four Guidelines", "section": "concepts", "type": "concept", "description": "Four foundational coding conduct rules for agents: Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven.", "created": "2026-08-22", "updated": "2026-08-24", "tags": [ "coding-guidelines", "agents", "principle" ], "sources": [ "raw/articles/karpathy-guidelines-skill-2026.md" ], "url": "https://pyweb.dev/wiki/karpathy-four-guidelines", "raw_markdown_url": "https://pyweb.dev/wiki/karpathy-four-guidelines.md" }, { "id": "wiki:llm-app-improvement-ladder", "slug": "llm-app-improvement-ladder", "title": "LLM App Improvement Ladder", "section": "concepts", "type": "concept", "description": "Matt Pocock's ordered ladder of 17 techniques for improving an LLM-powered app — from prompt basics to fine-tuning — try the simple thing first.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "llm-fundamentals", "patterns", "quality" ], "sources": [ "raw/aihero/how-to-improve-your-llm-powered-app.md" ], "url": "https://pyweb.dev/wiki/llm-app-improvement-ladder", "raw_markdown_url": "https://pyweb.dev/wiki/llm-app-improvement-ladder.md" }, { "id": "wiki:llm-message-protocol", "slug": "llm-message-protocol", "title": "LLM Message Protocol", "section": "concepts", "type": "concept", "description": "The message-based conversation protocol between application and LLM: system prompts, user/assistant messages, tool calls, and tool results.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "agents", "context-engineering", "llm-fundamentals" ], "sources": [ "raw/aihero-video/e00k46QugaOBLd4ZrIj3hR8DFSm01xZL2WhSAym3xNoa00.md", "raw/aihero-video/ogTZkRIjv00qmTh6B8MpqpSdKOVl2lYQHUcZOohLg007o.md", "raw/articles/aihero-ai-coding-dictionary-2026.md" ], "url": "https://pyweb.dev/wiki/llm-message-protocol", "raw_markdown_url": "https://pyweb.dev/wiki/llm-message-protocol.md" }, { "id": "wiki:llm-wiki-pattern", "slug": "llm-wiki-pattern", "title": "LLM Wiki Pattern", "section": "concepts", "type": "concept", "description": "Compounding, interlinked markdown knowledge base pattern curated autonomously by agents.", "created": "2026-08-22", "updated": "2026-08-24", "tags": [ "knowledge-management", "agents", "technique" ], "sources": [ "raw/articles/karpathy-guidelines-skill-2026.md", "raw/articles/karpathy-wiki-ecosystem-analysis-2026.md" ], "url": "https://pyweb.dev/wiki/llm-wiki-pattern", "raw_markdown_url": "https://pyweb.dev/wiki/llm-wiki-pattern.md" }, { "id": "wiki:model-context-protocol-basics", "slug": "model-context-protocol-basics", "title": "Model Context Protocol Basics", "section": "concepts", "type": "concept", "description": "MCP as the standardized bridge between LLM applications and external tools/data — the client-server layer beneath tool calling.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "agents", "tool-use", "protocols", "llm-fundamentals" ], "sources": [ "raw/aihero-video/Qy8eUULqAyzkPzbq6YkSYPhrcrc00q01A5W01zzBYcAb01Y.md", "raw/aihero-video/21vr8u5N01YJ023LXY00cjR01rWQXb1mpC2bVOibt64obKo.md", "raw/aihero/using-mcp-prompts.md", "raw/aihero/logging-a-huge-mcp-footgun.md", "raw/aihero/how-does-the-model-context-protocol-work.md" ], "url": "https://pyweb.dev/wiki/model-context-protocol-basics", "raw_markdown_url": "https://pyweb.dev/wiki/model-context-protocol-basics.md" }, { "id": "wiki:model-provider-abstraction", "slug": "model-provider-abstraction", "title": "Model Provider Abstraction", "section": "concepts", "type": "concept", "description": "Why production LLM apps need a provider-neutral interface — and the real switching cost when you code directly against one vendor's API.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "llm-fundamentals", "architecture", "patterns" ], "sources": [ "raw/aihero-video/8SB4g02p1OORs01RhtXt4YCadPPjcfgNr8KsbejDkVxFI.md", "raw/aihero-video/pEqcLrdb41402x028ndrEq2h24A51RkYC01yzqpfG4QJKo.md", "raw/aihero-video/cA6c02ZOSu7MxDK8I9z02J008OS3fwc01LkxNEiZW61DMhg.md", "raw/aihero-video/M02v00KLiYejPc55vWKBI6GETh6NM7Frcewj2i00q1oTyo.md" ], "url": "https://pyweb.dev/wiki/model-provider-abstraction", "raw_markdown_url": "https://pyweb.dev/wiki/model-provider-abstraction.md" }, { "id": "wiki:multi-agent-orchestration", "slug": "multi-agent-orchestration", "title": "Multi-Agent Orchestration", "section": "concepts", "type": "concept", "description": "Hierarchical agent swarms where engineers orchestrate fleets of specialized agents in parallel isolated worktrees: coder to conductor to orchestrator.", "created": "2026-08-24", "updated": "2026-08-30", "tags": [ "agents", "workflow", "subagents", "context-engineering", "evaluation" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md", "raw/articles/anthropic-multi-agent-research-system-2025.md" ], "url": "https://pyweb.dev/wiki/multi-agent-orchestration", "raw_markdown_url": "https://pyweb.dev/wiki/multi-agent-orchestration.md" }, { "id": "wiki:onion-architecture", "slug": "onion-architecture", "title": "Onion Architecture", "section": "concepts", "type": "concept", "description": null, "created": "2026-08-25", "updated": "2026-08-25", "tags": [ "principle", "workflow" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/onion-architecture", "raw_markdown_url": "https://pyweb.dev/wiki/onion-architecture.md" }, { "id": "wiki:progressive-disclosure", "slug": "progressive-disclosure", "title": "Progressive Disclosure", "section": "concepts", "type": "concept", "description": "Providing context and tooling to AI agents in staged layers on-demand rather than up front.", "created": "2026-08-22", "updated": "2026-08-30", "tags": [ "agents", "context-engineering", "skills" ], "sources": [ "raw/articles/aihero-dev-homepage-2026.md", "raw/articles/volcengine-openviking-2026.md" ], "url": "https://pyweb.dev/wiki/progressive-disclosure", "raw_markdown_url": "https://pyweb.dev/wiki/progressive-disclosure.md" }, { "id": "wiki:prompt-bloat", "slug": "prompt-bloat", "title": "Prompt Bloat", "section": "concepts", "type": "concept", "description": "The accumulation of redundant, generic, or conflicting instructions in system prompts that degrades agent performance.", "created": "2026-08-22", "updated": "2026-08-24", "tags": [ "agents", "context-engineering", "anti-patterns" ], "sources": [ "raw/articles/aihero-dev-homepage-2026.md" ], "url": "https://pyweb.dev/wiki/prompt-bloat", "raw_markdown_url": "https://pyweb.dev/wiki/prompt-bloat.md" }, { "id": "wiki:red-green-tdd", "slug": "red-green-tdd", "title": "Red/Green TDD", "section": "concepts", "type": "concept", "description": "Test-first development where failing tests are observed before writing minimal implementation code - the core discipline for coding agents.", "created": "2026-08-22", "updated": "2026-08-30", "tags": [ "tdd", "workflow", "agents", "coding-guidelines" ], "sources": [ "raw/articles/simon-willison-red-green-tdd-2026.md", "raw/articles/kent-beck-gergely-orosz-tdd-ai-agents-2025.md" ], "url": "https://pyweb.dev/wiki/red-green-tdd", "raw_markdown_url": "https://pyweb.dev/wiki/red-green-tdd.md" }, { "id": "wiki:releasable-patch-rate", "slug": "releasable-patch-rate", "title": "Releasable Patch Rate", "section": "concepts", "type": "concept", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "agentic-patterns", "code-quality", "workflow" ], "sources": [ "raw/articles/agentic-engineering-systems-evidence-report-2026.md", "raw/articles/addy-osmani-agentic-code-quality-2026.md", "raw/articles/dora-ai-assisted-software-development-2025.md" ], "url": "https://pyweb.dev/wiki/releasable-patch-rate", "raw_markdown_url": "https://pyweb.dev/wiki/releasable-patch-rate.md" }, { "id": "wiki:site-as-eval-subject-grading", "slug": "site-as-eval-subject-grading", "title": "Site-as-Eval-Subject Grading", "section": "concepts", "type": "concept", "description": "Grading a static site with deterministic graders and LLM judges, then hill-climbing the design against the scorecard.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "evaluation", "agents", "technique", "workflow" ], "sources": [ "raw/articles/hamel-husain-ai-evals-faq-2026.md", "raw/articles/airbnb-eval-driven-development-2026.md" ], "url": "https://pyweb.dev/wiki/site-as-eval-subject-grading", "raw_markdown_url": "https://pyweb.dev/wiki/site-as-eval-subject-grading.md" }, { "id": "wiki:skill-treatment-effect", "slug": "skill-treatment-effect", "title": "Skill Treatment Effect", "section": "concepts", "type": "concept", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "agentic-patterns", "evaluation", "harness-engineering" ], "sources": [ "raw/papers/skillsbench-2026.md", "raw/papers/swe-skills-bench-2026.md", "raw/articles/addy-osmani-agent-skills-2026.md" ], "url": "https://pyweb.dev/wiki/skill-treatment-effect", "raw_markdown_url": "https://pyweb.dev/wiki/skill-treatment-effect.md" }, { "id": "wiki:smart-zone", "slug": "smart-zone", "title": "Smart Zone", "section": "concepts", "type": "concept", "description": "The optimal token window where frontier LLMs maintain peak reasoning sharpness before attention degradation sets in.", "created": "2026-08-22", "updated": "2026-08-27", "tags": [ "agents", "context-engineering", "workflow" ], "sources": [ "raw/articles/aihero-dev-homepage-2026.md", "raw/articles/aihero-ai-coding-dictionary-2026.md" ], "url": "https://pyweb.dev/wiki/smart-zone", "raw_markdown_url": "https://pyweb.dev/wiki/smart-zone.md" }, { "id": "wiki:software-engineering-fundamentals-for-agents", "slug": "software-engineering-fundamentals-for-agents", "title": "Software Engineering Fundamentals for Agents", "section": "concepts", "type": "concept", "description": null, "created": "2026-08-29", "updated": "2026-08-29", "tags": [ "agentic-patterns", "architecture", "workflow", "code-quality" ], "sources": [], "url": "https://pyweb.dev/wiki/software-engineering-fundamentals-for-agents", "raw_markdown_url": "https://pyweb.dev/wiki/software-engineering-fundamentals-for-agents.md" }, { "id": "wiki:structured-outputs", "slug": "structured-outputs", "title": "Structured Outputs", "section": "concepts", "type": "concept", "description": "Constraining LLM responses to JSON-schema shapes — objects, enums, arrays — for data extraction and classification, with streaming and tool-based variants.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "llm-fundamentals", "context-engineering", "patterns" ], "sources": [ "raw/aihero-video/wiUXxKeFSz8JTwQvmZ7ut029nJ23PevCst8ylkrCHtTU.md", "raw/aihero-video/NR9LollfJgzuMq02zxZn6nnhQjMVcTQ2vkhvc8Xz2025U.md", "raw/aihero-video/uygTjLE2W4XQs5Qla01MRI1arhqTtui2gOCQqFMlIlEs.md", "raw/aihero-video/ZxadOHgUN02s99h3Jhp01TwEcbgKVmWUkA9qnwOM3eMI4.md", "raw/aihero-video/PG15cq802CeSluIc6YM7CV927SX01MbOUpQ01FBVXN8WlI.md" ], "url": "https://pyweb.dev/wiki/structured-outputs", "raw_markdown_url": "https://pyweb.dev/wiki/structured-outputs.md" }, { "id": "wiki:subagents-and-context-management", "slug": "subagents-and-context-management", "title": "Subagents and Context Management", "section": "concepts", "type": "concept", "description": "Preserving root conversation context by dispatching isolated sub-agents for repo exploration, testing, debugging, and file edits.", "created": "2026-08-22", "updated": "2026-08-30", "tags": [ "agents", "subagents", "context-engineering", "workflow" ], "sources": [ "raw/articles/simon-willison-subagents-2026.md", "raw/articles/simon-willison-how-coding-agents-work-2026.md" ], "url": "https://pyweb.dev/wiki/subagents-and-context-management", "raw_markdown_url": "https://pyweb.dev/wiki/subagents-and-context-management.md" }, { "id": "wiki:tdd-with-agents", "slug": "tdd-with-agents", "title": "TDD With Agents", "section": "concepts", "type": "concept", "description": "Rigorous test-driven development loop using executable tests as the truth referee for coding agents.", "created": "2026-08-22", "updated": "2026-08-24", "tags": [ "tdd", "workflow", "agents", "technique" ], "sources": [ "raw/articles/karpathy-guidelines-skill-2026.md", "raw/articles/aihero-dev-homepage-2026.md", "raw/articles/simon-willison-red-green-tdd-2026.md" ], "url": "https://pyweb.dev/wiki/tdd-with-agents", "raw_markdown_url": "https://pyweb.dev/wiki/tdd-with-agents.md" }, { "id": "wiki:think-tool", "slug": "think-tool", "title": "Think Tool", "section": "concepts", "type": "concept", "description": "Anthropic's technique of giving an LLM a no-op 'think' tool so it can persist structured reasoning into context before complex tool calls.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "agents", "tool-use", "patterns" ], "sources": [ "raw/aihero/implementing-anthropics-think-tool-in-typescript.md" ], "url": "https://pyweb.dev/wiki/think-tool", "raw_markdown_url": "https://pyweb.dev/wiki/think-tool.md" }, { "id": "wiki:tool-calling-loop", "slug": "tool-calling-loop", "title": "Tool Calling Loop", "section": "concepts", "type": "concept", "description": "The four-step agentic loop — specify tools, receive tool calls, execute locally, return results — that lets LLMs act on the world.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "agents", "tool-use", "llm-fundamentals" ], "sources": [ "raw/aihero-video/1A6SlQWRqgl36X8wnIsExGcsoMF02k3t7A7aohekf9MY.md", "raw/aihero-video/b94i4u00v5pvsu7W4K5vZoIDCaAcoiaXrOWMnsKGmXAs.md", "raw/aihero-video/knNhtS36aC5dWvpI5RNAu8anohJufCyfurIVHQKZfNw.md", "raw/aihero-video/OS36qkqDQo1J01Nf7EUcisLYfKJ6zilncehUsDq1beKg.md" ], "url": "https://pyweb.dev/wiki/tool-calling-loop", "raw_markdown_url": "https://pyweb.dev/wiki/tool-calling-loop.md" }, { "id": "wiki:tracer-bullets", "slug": "tracer-bullets", "title": "Tracer Bullets", "section": "concepts", "type": "concept", "description": "Shipping the thinnest end-to-end slice through all architecture layers before expanding features.", "created": "2026-08-22", "updated": "2026-08-30", "tags": [ "workflow", "agents", "technique" ], "sources": [ "raw/articles/aihero-dev-homepage-2026.md" ], "url": "https://pyweb.dev/wiki/tracer-bullets", "raw_markdown_url": "https://pyweb.dev/wiki/tracer-bullets.md" }, { "id": "wiki:addy-osmani", "slug": "addy-osmani", "title": "Addy Osmani", "section": "entities", "type": "entity", "description": "Engineering leader and author writing on agent harness engineering, agentic code quality gates, and software factory workflows.", "created": "2026-08-24", "updated": "2026-08-27", "tags": [ "person", "workflow" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md", "raw/articles/addy-osmani-agentic-code-quality-2026.md" ], "url": "https://pyweb.dev/wiki/addy-osmani", "raw_markdown_url": "https://pyweb.dev/wiki/addy-osmani.md" }, { "id": "wiki:aditi-raghunathan", "slug": "aditi-raghunathan", "title": "Aditi Raghunathan", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/adversarial-hacker-fixer-verifiers-2026.md" ], "url": "https://pyweb.dev/wiki/aditi-raghunathan", "raw_markdown_url": "https://pyweb.dev/wiki/aditi-raghunathan.md" }, { "id": "wiki:ahmed-e-hassan", "slug": "ahmed-e-hassan", "title": "Ahmed E. Hassan", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/agentic-pull-requests-github-2026.md", "raw/papers/aidev-dataset-2026.md" ], "url": "https://pyweb.dev/wiki/ahmed-e-hassan", "raw_markdown_url": "https://pyweb.dev/wiki/ahmed-e-hassan.md" }, { "id": "wiki:airbnb", "slug": "airbnb", "title": "Airbnb", "section": "entities", "type": "entity", "description": "Global travel marketplace and engineering pioneer in industrial Eval-Driven Development (EDD) for generative AI applications.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "organization", "evaluation", "workflow" ], "sources": [], "url": "https://pyweb.dev/wiki/airbnb", "raw_markdown_url": "https://pyweb.dev/wiki/airbnb.md" }, { "id": "wiki:alistair-cockburn", "slug": "alistair-cockburn", "title": "Alistair Cockburn", "section": "entities", "type": "entity", "description": null, "created": "2026-08-25", "updated": "2026-08-25", "tags": [ "person", "educator" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/alistair-cockburn", "raw_markdown_url": "https://pyweb.dev/wiki/alistair-cockburn.md" }, { "id": "wiki:andrei-botocan", "slug": "andrei-botocan", "title": "Andrei Botocan", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/autonomous-agent-contributions-wild-2026.md" ], "url": "https://pyweb.dev/wiki/andrei-botocan", "raw_markdown_url": "https://pyweb.dev/wiki/andrei-botocan.md" }, { "id": "wiki:andrej-karpathy", "slug": "andrej-karpathy", "title": "Andrej Karpathy", "section": "entities", "type": "entity", "description": "AI researcher, educator, Stanford CS231n co-creator, and developer of the build-from-scratch pedagogy.", "created": "2026-08-22", "updated": "2026-08-24", "tags": [ "person", "educator", "agents", "pedagogy" ], "sources": [ "raw/articles/karpathy-guidelines-skill-2026.md", "raw/articles/agentic-engineering-trends-2026-synthesis.md" ], "url": "https://pyweb.dev/wiki/andrej-karpathy", "raw_markdown_url": "https://pyweb.dev/wiki/andrej-karpathy.md" }, { "id": "wiki:andrew-ng", "slug": "andrew-ng", "title": "Andrew Ng", "section": "entities", "type": "entity", "description": null, "created": "2026-08-29", "updated": "2026-08-29", "tags": [ "person", "educator" ], "sources": [], "url": "https://pyweb.dev/wiki/andrew-ng", "raw_markdown_url": "https://pyweb.dev/wiki/andrew-ng.md" }, { "id": "wiki:anil-madhavapeddy", "slug": "anil-madhavapeddy", "title": "Anil Madhavapeddy", "section": "entities", "type": "entity", "description": null, "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "person", "security" ], "sources": [ "raw/articles/simon-willison-just-a-rumour-of-a-bug-is-enough-to-find-a-security-exploit-2026.md" ], "url": "https://pyweb.dev/wiki/anil-madhavapeddy", "raw_markdown_url": "https://pyweb.dev/wiki/anil-madhavapeddy.md" }, { "id": "wiki:anthropic", "slug": "anthropic", "title": "Anthropic", "section": "entities", "type": "entity", "description": "AI safety research company developing Claude LLM models and researching agent systems.", "created": "2026-08-24", "updated": "2026-08-30", "tags": [ "company", "agents", "evaluation", "security" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md", "raw/articles/anthropic-multi-agent-research-system-2025.md", "raw/articles/anthropic-engineering-how-we-contain-claude-2026.md", "raw/articles/anthropic-engineering-claude-code-auto-mode-2026.md", "raw/articles/anthropic-claude-managed-agents-overview-2026.md" ], "url": "https://pyweb.dev/wiki/anthropic", "raw_markdown_url": "https://pyweb.dev/wiki/anthropic.md" }, { "id": "wiki:armin-ronacher", "slug": "armin-ronacher", "title": "Armin Ronacher", "section": "entities", "type": "entity", "description": "Software engineer critiquing coordination friction loss in agent-accelerated development.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "person", "principle" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md" ], "url": "https://pyweb.dev/wiki/armin-ronacher", "raw_markdown_url": "https://pyweb.dev/wiki/armin-ronacher.md" }, { "id": "wiki:beatrice-casey", "slug": "beatrice-casey", "title": "Beatrice Casey", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/security-agentic-pull-requests-2026.md" ], "url": "https://pyweb.dev/wiki/beatrice-casey", "raw_markdown_url": "https://pyweb.dev/wiki/beatrice-casey.md" }, { "id": "wiki:beth-barnes", "slug": "beth-barnes", "title": "Beth Barnes", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/metr-developer-productivity-rct-2025.md" ], "url": "https://pyweb.dev/wiki/beth-barnes", "raw_markdown_url": "https://pyweb.dev/wiki/beth-barnes.md" }, { "id": "wiki:boris-cherny", "slug": "boris-cherny", "title": "Boris Cherny", "section": "entities", "type": "entity", "description": "Engineering leader at Anthropic, creator of Claude Code, and author of Programming TypeScript.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person", "authority", "workflow" ], "sources": [], "url": "https://pyweb.dev/wiki/boris-cherny", "raw_markdown_url": "https://pyweb.dev/wiki/boris-cherny.md" }, { "id": "wiki:brittany-reid", "slug": "brittany-reid", "title": "Brittany Reid", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/agentic-pull-requests-github-2026.md" ], "url": "https://pyweb.dev/wiki/brittany-reid", "raw_markdown_url": "https://pyweb.dev/wiki/brittany-reid.md" }, { "id": "wiki:cathryn-lavery", "slug": "cathryn-lavery", "title": "Cathryn Lavery", "section": "entities", "type": "entity", "description": "Designer, entrepreneur, and author of Diagram Design; pioneer of editorial visual design systems and semantic diagramming for AI coding agents.", "created": "2026-08-23", "updated": "2026-08-23", "tags": [ "person", "educator", "agents", "diagrams" ], "sources": [ "raw/articles/cathryn-lavery-diagram-design-2026.md" ], "url": "https://pyweb.dev/wiki/cathryn-lavery", "raw_markdown_url": "https://pyweb.dev/wiki/cathryn-lavery.md" }, { "id": "wiki:christoph-csallner", "slug": "christoph-csallner", "title": "Christoph Csallner", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/tests-agentic-pull-requests-2026.md" ], "url": "https://pyweb.dev/wiki/christoph-csallner", "raw_markdown_url": "https://pyweb.dev/wiki/christoph-csallner.md" }, { "id": "wiki:christoph-nakazawa", "slug": "christoph-nakazawa", "title": "Christoph Nakazawa", "section": "entities", "type": "entity", "description": null, "created": "2026-08-28", "updated": "2026-08-28", "tags": [ "person", "coding-guidelines", "feedback-loops" ], "sources": [ "raw/articles/nkzw-oxlint-config-2026.md" ], "url": "https://pyweb.dev/wiki/christoph-nakazawa", "raw_markdown_url": "https://pyweb.dev/wiki/christoph-nakazawa.md" }, { "id": "wiki:copilotkit", "slug": "copilotkit", "title": "CopilotKit", "section": "entities", "type": "entity", "description": "Open-source AI Copilot framework and creators of the AG-UI protocol for agent-user interaction.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "company", "agents", "workflow" ], "sources": [], "url": "https://pyweb.dev/wiki/copilotkit", "raw_markdown_url": "https://pyweb.dev/wiki/copilotkit.md" }, { "id": "wiki:cursor", "slug": "cursor", "title": "Cursor", "section": "entities", "type": "entity", "description": "AI-powered code editor company pioneering hierarchical agent systems for autonomous coding.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "company", "agents", "workflow" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md" ], "url": "https://pyweb.dev/wiki/cursor", "raw_markdown_url": "https://pyweb.dev/wiki/cursor.md" }, { "id": "wiki:david-gros", "slug": "david-gros", "title": "David Gros", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/autonomous-agent-contributions-wild-2026.md" ], "url": "https://pyweb.dev/wiki/david-gros", "raw_markdown_url": "https://pyweb.dev/wiki/david-gros.md" }, { "id": "wiki:david-rein", "slug": "david-rein", "title": "David Rein", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/metr-developer-productivity-rct-2025.md" ], "url": "https://pyweb.dev/wiki/david-rein", "raw_markdown_url": "https://pyweb.dev/wiki/david-rein.md" }, { "id": "wiki:deepseek", "slug": "deepseek", "title": "DeepSeek", "section": "entities", "type": "entity", "description": "AI research company behind frontier open-weights models and the DeepSeek Harness agent runtime developer preview.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "company", "agents" ], "sources": [], "url": "https://pyweb.dev/wiki/deepseek", "raw_markdown_url": "https://pyweb.dev/wiki/deepseek.md" }, { "id": "wiki:dipayan-banik", "slug": "dipayan-banik", "title": "Dipayan Banik", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/code-review-agents-empirical-study-2026.md" ], "url": "https://pyweb.dev/wiki/dipayan-banik", "raw_markdown_url": "https://pyweb.dev/wiki/dipayan-banik.md" }, { "id": "wiki:dora", "slug": "dora", "title": "DORA", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "company", "evaluation" ], "sources": [ "raw/articles/dora-ai-assisted-software-development-2025.md" ], "url": "https://pyweb.dev/wiki/dora", "raw_markdown_url": "https://pyweb.dev/wiki/dora.md" }, { "id": "wiki:drew-breunig", "slug": "drew-breunig", "title": "Drew Breunig", "section": "entities", "type": "entity", "description": "Writer on LLM economics; argued in 'Fable & The End of the Free Lunch' that high frontier-model pricing ended the era when new models papered over weak harnesses.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "person", "agents", "context-engineering" ], "sources": [ "raw/articles/simon-willison-quoting-drew-breunig-2026.md", "raw/articles/simon-willison-anthropic-s-best-ai-model-struggles-to-attract-users-as-chea-2026.md" ], "url": "https://pyweb.dev/wiki/drew-breunig", "raw_markdown_url": "https://pyweb.dev/wiki/drew-breunig.md" }, { "id": "wiki:dung-nguyen-manh", "slug": "dung-nguyen-manh", "title": "Dung Nguyen Manh", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/swe-evo-long-horizon-2026.md" ], "url": "https://pyweb.dev/wiki/dung-nguyen-manh", "raw_markdown_url": "https://pyweb.dev/wiki/dung-nguyen-manh.md" }, { "id": "wiki:eirini-kalliamvakou", "slug": "eirini-kalliamvakou", "title": "Eirini Kalliamvakou", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/github-copilot-productivity-experiment-2023.md" ], "url": "https://pyweb.dev/wiki/eirini-kalliamvakou", "raw_markdown_url": "https://pyweb.dev/wiki/eirini-kalliamvakou.md" }, { "id": "wiki:epoch-ai", "slug": "epoch-ai", "title": "Epoch AI", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "company", "evaluation" ], "sources": [ "raw/articles/epoch-swe-bench-verified-analysis-2025.md" ], "url": "https://pyweb.dev/wiki/epoch-ai", "raw_markdown_url": "https://pyweb.dev/wiki/epoch-ai.md" }, { "id": "wiki:florian-brand", "slug": "florian-brand", "title": "Florian Brand", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/articles/epoch-swe-bench-verified-analysis-2025.md" ], "url": "https://pyweb.dev/wiki/florian-brand", "raw_markdown_url": "https://pyweb.dev/wiki/florian-brand.md" }, { "id": "wiki:gelei-deng", "slug": "gelei-deng", "title": "Gelei Deng", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/overeager-coding-agents-2026.md" ], "url": "https://pyweb.dev/wiki/gelei-deng", "raw_markdown_url": "https://pyweb.dev/wiki/gelei-deng.md" }, { "id": "wiki:gergely-orosz", "slug": "gergely-orosz", "title": "Gergely Orosz", "section": "entities", "type": "entity", "description": "Author of The Pragmatic Engineer newsletter, covering tech industry trends, engineering leadership, and developer tooling in the agentic era.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person", "authority", "workflow" ], "sources": [], "url": "https://pyweb.dev/wiki/gergely-orosz", "raw_markdown_url": "https://pyweb.dev/wiki/gergely-orosz.md" }, { "id": "wiki:github", "slug": "github", "title": "GitHub", "section": "entities", "type": "entity", "description": "Leading software development platform, developer of Copilot, and author of the Spec-Driven Development toolkit for AI agents.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "organization", "workflow", "tool-use" ], "sources": [], "url": "https://pyweb.dev/wiki/github", "raw_markdown_url": "https://pyweb.dev/wiki/github.md" }, { "id": "wiki:hajimu-iida", "slug": "hajimu-iida", "title": "Hajimu Iida", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/agent-generated-code-maintenance-2026.md", "raw/papers/agentic-pull-requests-github-2026.md" ], "url": "https://pyweb.dev/wiki/hajimu-iida", "raw_markdown_url": "https://pyweb.dev/wiki/hajimu-iida.md" }, { "id": "wiki:hamel-husain", "slug": "hamel-husain", "title": "Hamel Husain", "section": "entities", "type": "entity", "description": "AI product engineer, machine learning educator, and specialist in LLM evaluation, error analysis, and domain-grounded AI systems.", "created": "2026-08-22", "updated": "2026-08-24", "tags": [ "person", "educator", "evaluation", "context-engineering" ], "sources": [ "raw/articles/hamel-ai-product-engineering-notes-2026.md", "raw/articles/parlance-labs-do-automated-evals-work-2026.md", "raw/articles/hamel-husain-do-automated-evals-work-2026.md", "raw/articles/hamel-husain-the-revenge-of-the-data-scientist-2026.md", "raw/articles/hamel-husain-it-s-hard-to-eval-is-a-product-smell-2026.md" ], "url": "https://pyweb.dev/wiki/hamel-husain", "raw_markdown_url": "https://pyweb.dev/wiki/hamel-husain.md" }, { "id": "wiki:hao-li", "slug": "hao-li", "title": "Hao Li", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/agentic-pull-requests-github-2026.md", "raw/papers/aidev-dataset-2026.md" ], "url": "https://pyweb.dev/wiki/hao-li", "raw_markdown_url": "https://pyweb.dev/wiki/hao-li.md" }, { "id": "wiki:haoxiang-zhang", "slug": "haoxiang-zhang", "title": "Haoxiang Zhang", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/aidev-dataset-2026.md" ], "url": "https://pyweb.dev/wiki/haoxiang-zhang", "raw_markdown_url": "https://pyweb.dev/wiki/haoxiang-zhang.md" }, { "id": "wiki:hiroshi-iwata", "slug": "hiroshi-iwata", "title": "Hiroshi Iwata", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/agent-generated-code-maintenance-2026.md" ], "url": "https://pyweb.dev/wiki/hiroshi-iwata", "raw_markdown_url": "https://pyweb.dev/wiki/hiroshi-iwata.md" }, { "id": "wiki:huy-nhat-phan", "slug": "huy-nhat-phan", "title": "Huy Nhat Phan", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/swe-evo-long-horizon-2026.md" ], "url": "https://pyweb.dev/wiki/huy-nhat-phan", "raw_markdown_url": "https://pyweb.dev/wiki/huy-nhat-phan.md" }, { "id": "wiki:ivan-bercovich", "slug": "ivan-bercovich", "title": "Ivan Bercovich", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/adversarial-hacker-fixer-verifiers-2026.md" ], "url": "https://pyweb.dev/wiki/ivan-bercovich", "raw_markdown_url": "https://pyweb.dev/wiki/ivan-bercovich.md" }, { "id": "wiki:ivar-jacobson", "slug": "ivar-jacobson", "title": "Ivar Jacobson", "section": "entities", "type": "entity", "description": null, "created": "2026-08-25", "updated": "2026-08-25", "tags": [ "person", "educator" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/ivar-jacobson", "raw_markdown_url": "https://pyweb.dev/wiki/ivar-jacobson.md" }, { "id": "wiki:ivgeni-segal", "slug": "ivgeni-segal", "title": "Ivgeni Segal", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/adversarial-hacker-fixer-verifiers-2026.md" ], "url": "https://pyweb.dev/wiki/ivgeni-segal", "raw_markdown_url": "https://pyweb.dev/wiki/ivgeni-segal.md" }, { "id": "wiki:james-coplien", "slug": "james-coplien", "title": "James Coplien", "section": "entities", "type": "entity", "description": null, "created": "2026-08-25", "updated": "2026-08-25", "tags": [ "person", "educator" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/james-coplien", "raw_markdown_url": "https://pyweb.dev/wiki/james-coplien.md" }, { "id": "wiki:james-shore", "slug": "james-shore", "title": "James Shore", "section": "entities", "type": "entity", "description": "Software engineering consultant analyzing economic implications of AI-accelerated development.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "person", "principle" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md" ], "url": "https://pyweb.dev/wiki/james-shore", "raw_markdown_url": "https://pyweb.dev/wiki/james-shore.md" }, { "id": "wiki:jarred-sumner", "slug": "jarred-sumner", "title": "Jarred Sumner", "section": "entities", "type": "entity", "description": "Creator of Bun, who led autonomous agent-driven rewrite of Bun's codebase from Zig to Rust.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "person", "agents", "evaluation" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md" ], "url": "https://pyweb.dev/wiki/jarred-sumner", "raw_markdown_url": "https://pyweb.dev/wiki/jarred-sumner.md" }, { "id": "wiki:jean-stanislas-denain", "slug": "jean-stanislas-denain", "title": "Jean-Stanislas Denain", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/articles/epoch-swe-bench-verified-analysis-2025.md" ], "url": "https://pyweb.dev/wiki/jean-stanislas-denain", "raw_markdown_url": "https://pyweb.dev/wiki/jean-stanislas-denain.md" }, { "id": "wiki:jeffrey-palermo", "slug": "jeffrey-palermo", "title": "Jeffrey Palermo", "section": "entities", "type": "entity", "description": null, "created": "2026-08-25", "updated": "2026-08-25", "tags": [ "person", "educator" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/jeffrey-palermo", "raw_markdown_url": "https://pyweb.dev/wiki/jeffrey-palermo.md" }, { "id": "wiki:joanna-c-s-santos", "slug": "joanna-c-s-santos", "title": "Joanna C. S. Santos", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/security-agentic-pull-requests-2026.md" ], "url": "https://pyweb.dev/wiki/joanna-c-s-santos", "raw_markdown_url": "https://pyweb.dev/wiki/joanna-c-s-santos.md" }, { "id": "wiki:joel-becker", "slug": "joel-becker", "title": "Joel Becker", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/metr-developer-productivity-rct-2025.md" ], "url": "https://pyweb.dev/wiki/joel-becker", "raw_markdown_url": "https://pyweb.dev/wiki/joel-becker.md" }, { "id": "wiki:johann-rehberger", "slug": "johann-rehberger", "title": "Johann Rehberger", "section": "entities", "type": "entity", "description": "Security researcher warning about normalization of deviance in AI system permissions.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "person", "agents", "anti-patterns" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md" ], "url": "https://pyweb.dev/wiki/johann-rehberger", "raw_markdown_url": "https://pyweb.dev/wiki/johann-rehberger.md" }, { "id": "wiki:k-m-ferdous", "slug": "k-m-ferdous", "title": "K M Ferdous", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/code-review-agents-empirical-study-2026.md" ], "url": "https://pyweb.dev/wiki/k-m-ferdous", "raw_markdown_url": "https://pyweb.dev/wiki/k-m-ferdous.md" }, { "id": "wiki:kenichi-yamaguchi", "slug": "kenichi-yamaguchi", "title": "Ken’ichi Yamaguchi", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/agent-generated-code-maintenance-2026.md" ], "url": "https://pyweb.dev/wiki/kenichi-yamaguchi", "raw_markdown_url": "https://pyweb.dev/wiki/kenichi-yamaguchi.md" }, { "id": "wiki:kent-beck", "slug": "kent-beck", "title": "Kent Beck", "section": "entities", "type": "entity", "description": "Pioneer of Extreme Programming (XP), Test-Driven Development (TDD), co-author of the Agile Manifesto, and author writing on AI coding workflows.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person", "authority", "tdd", "workflow" ], "sources": [], "url": "https://pyweb.dev/wiki/kent-beck", "raw_markdown_url": "https://pyweb.dev/wiki/kent-beck.md" }, { "id": "wiki:kexun-zhang", "slug": "kexun-zhang", "title": "Kexun Zhang", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/adversarial-hacker-fixer-verifiers-2026.md" ], "url": "https://pyweb.dev/wiki/kexun-zhang", "raw_markdown_url": "https://pyweb.dev/wiki/kexun-zhang.md" }, { "id": "wiki:kowshik-chowdhury", "slug": "kowshik-chowdhury", "title": "Kowshik Chowdhury", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/code-review-agents-empirical-study-2026.md" ], "url": "https://pyweb.dev/wiki/kowshik-chowdhury", "raw_markdown_url": "https://pyweb.dev/wiki/kowshik-chowdhury.md" }, { "id": "wiki:lalit-maganti", "slug": "lalit-maganti", "title": "Lalit Maganti", "section": "entities", "type": "entity", "description": "Syntaqlite creator documenting where coding agents help implementation and harm unresolved design work.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "person", "agents", "anti-patterns", "workflow" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md" ], "url": "https://pyweb.dev/wiki/lalit-maganti", "raw_markdown_url": "https://pyweb.dev/wiki/lalit-maganti.md" }, { "id": "wiki:leo-yu-zhang", "slug": "leo-yu-zhang", "title": "Leo Yu Zhang", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/overeager-coding-agents-2026.md" ], "url": "https://pyweb.dev/wiki/leo-yu-zhang", "raw_markdown_url": "https://pyweb.dev/wiki/leo-yu-zhang.md" }, { "id": "wiki:maliheh-izadi", "slug": "maliheh-izadi", "title": "Maliheh Izadi", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/autonomous-agent-contributions-wild-2026.md" ], "url": "https://pyweb.dev/wiki/maliheh-izadi", "raw_markdown_url": "https://pyweb.dev/wiki/maliheh-izadi.md" }, { "id": "wiki:mario-zechner", "slug": "mario-zechner", "title": "Mario Zechner", "section": "entities", "type": "entity", "description": "Software engineer warning about compounding errors in high-velocity agent development.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "person", "principle" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md" ], "url": "https://pyweb.dev/wiki/mario-zechner", "raw_markdown_url": "https://pyweb.dev/wiki/mario-zechner.md" }, { "id": "wiki:martin-fowler", "slug": "martin-fowler", "title": "Martin Fowler", "section": "entities", "type": "entity", "description": "Author, chief scientist at ThoughtWorks, and foundational thinker on software architecture, refactoring, and AI-assisted engineering practices.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person", "authority", "workflow" ], "sources": [], "url": "https://pyweb.dev/wiki/martin-fowler", "raw_markdown_url": "https://pyweb.dev/wiki/martin-fowler.md" }, { "id": "wiki:matt-pocock", "slug": "matt-pocock", "title": "Matt Pocock", "section": "entities", "type": "entity", "description": "TypeScript and AI engineering educator behind the idea-to-ship workflow and deep module design.", "created": "2026-08-22", "updated": "2026-08-30", "tags": [ "person", "educator", "workflow", "agents" ], "sources": [ "raw/articles/matt-pocock-interviews-2023.md", "raw/articles/aihero-dev-homepage-2026.md", "raw/articles/mattpocock-skills-repo-2026.md", "raw/articles/aihero-ai-coding-dictionary-2026.md", "raw/aihero-video/gL4LhjWghmYEdDOI402Z6KUXkPdwhwNAtO52EF6DHkcw.md" ], "url": "https://pyweb.dev/wiki/matt-pocock", "raw_markdown_url": "https://pyweb.dev/wiki/matt-pocock.md" }, { "id": "wiki:mert-demirer", "slug": "mert-demirer", "title": "Mert Demirer", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/github-copilot-productivity-experiment-2023.md" ], "url": "https://pyweb.dev/wiki/mert-demirer", "raw_markdown_url": "https://pyweb.dev/wiki/mert-demirer.md" }, { "id": "wiki:miku-watanabe", "slug": "miku-watanabe", "title": "Miku Watanabe", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/agentic-pull-requests-github-2026.md" ], "url": "https://pyweb.dev/wiki/miku-watanabe", "raw_markdown_url": "https://pyweb.dev/wiki/miku-watanabe.md" }, { "id": "wiki:minh-vu-thai-pham", "slug": "minh-vu-thai-pham", "title": "Minh Vu Thai Pham", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/swe-evo-long-horizon-2026.md" ], "url": "https://pyweb.dev/wiki/minh-vu-thai-pham", "raw_markdown_url": "https://pyweb.dev/wiki/minh-vu-thai-pham.md" }, { "id": "wiki:model-evaluation-and-threat-research", "slug": "model-evaluation-and-threat-research", "title": "Model Evaluation & Threat Research", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "company", "evaluation" ], "sources": [ "raw/articles/metr-task-completion-time-horizons-2026.md", "raw/papers/metr-developer-productivity-rct-2025.md" ], "url": "https://pyweb.dev/wiki/model-evaluation-and-threat-research", "raw_markdown_url": "https://pyweb.dev/wiki/model-evaluation-and-threat-research.md" }, { "id": "wiki:mohammed-latif-siddiq", "slug": "mohammed-latif-siddiq", "title": "Mohammed Latif Siddiq", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/security-agentic-pull-requests-2026.md" ], "url": "https://pyweb.dev/wiki/mohammed-latif-siddiq", "raw_markdown_url": "https://pyweb.dev/wiki/mohammed-latif-siddiq.md" }, { "id": "wiki:nat-pryce", "slug": "nat-pryce", "title": "Nat Pryce", "section": "entities", "type": "entity", "description": null, "created": "2026-08-25", "updated": "2026-08-25", "tags": [ "person", "educator" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/nat-pryce", "raw_markdown_url": "https://pyweb.dev/wiki/nat-pryce.md" }, { "id": "wiki:nate-rush", "slug": "nate-rush", "title": "Nate Rush", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/metr-developer-productivity-rct-2025.md" ], "url": "https://pyweb.dev/wiki/nate-rush", "raw_markdown_url": "https://pyweb.dev/wiki/nate-rush.md" }, { "id": "wiki:nghi-d-q-bui", "slug": "nghi-d-q-bui", "title": "Nghi D. Q. Bui", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/swe-evo-long-horizon-2026.md" ], "url": "https://pyweb.dev/wiki/nghi-d-q-bui", "raw_markdown_url": "https://pyweb.dev/wiki/nghi-d-q-bui.md" }, { "id": "wiki:nick-craig-wood", "slug": "nick-craig-wood", "title": "Nick Craig-Wood", "section": "entities", "type": "entity", "description": null, "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "person", "security", "workflow" ], "sources": [ "raw/articles/simon-willison-just-a-rumour-of-a-bug-is-enough-to-find-a-security-exploit-2026.md" ], "url": "https://pyweb.dev/wiki/nick-craig-wood", "raw_markdown_url": "https://pyweb.dev/wiki/nick-craig-wood.md" }, { "id": "wiki:openai", "slug": "openai", "title": "OpenAI", "section": "entities", "type": "entity", "description": "AI research and deployment company developing GPT models, ChatGPT, Codex, and agent harness infrastructure.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "company", "agents", "evaluation", "security" ], "sources": [], "url": "https://pyweb.dev/wiki/openai", "raw_markdown_url": "https://pyweb.dev/wiki/openai.md" }, { "id": "wiki:peter-cihon", "slug": "peter-cihon", "title": "Peter Cihon", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/github-copilot-productivity-experiment-2023.md" ], "url": "https://pyweb.dev/wiki/peter-cihon", "raw_markdown_url": "https://pyweb.dev/wiki/peter-cihon.md" }, { "id": "wiki:prem-devanbu", "slug": "prem-devanbu", "title": "Prem Devanbu", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/autonomous-agent-contributions-wild-2026.md" ], "url": "https://pyweb.dev/wiki/prem-devanbu", "raw_markdown_url": "https://pyweb.dev/wiki/prem-devanbu.md" }, { "id": "wiki:prithvi-rajasekaran", "slug": "prithvi-rajasekaran", "title": "Prithvi Rajasekaran", "section": "entities", "type": "entity", "description": null, "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "person", "agents", "evaluation" ], "sources": [ "raw/articles/anthropic-engineering-harness-design-long-running-apps-2026.md" ], "url": "https://pyweb.dev/wiki/prithvi-rajasekaran", "raw_markdown_url": "https://pyweb.dev/wiki/prithvi-rajasekaran.md" }, { "id": "wiki:rahul-pandita", "slug": "rahul-pandita", "title": "Rahul Pandita", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/autonomous-agent-contributions-wild-2026.md" ], "url": "https://pyweb.dev/wiki/rahul-pandita", "raw_markdown_url": "https://pyweb.dev/wiki/rahul-pandita.md" }, { "id": "wiki:razvan-mihai-popescu", "slug": "razvan-mihai-popescu", "title": "Razvan Mihai Popescu", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/autonomous-agent-contributions-wild-2026.md" ], "url": "https://pyweb.dev/wiki/razvan-mihai-popescu", "raw_markdown_url": "https://pyweb.dev/wiki/razvan-mihai-popescu.md" }, { "id": "wiki:richard-feynman", "slug": "richard-feynman", "title": "Richard Feynman", "section": "entities", "type": "entity", "description": "Nobel laureate physicist known for first-principles thinking, joyful curiosity, and plain-language pedagogy.", "created": "2026-08-22", "updated": "2026-08-24", "tags": [ "person", "physicist", "teaching", "worldview" ], "sources": [ "raw/articles/aihero-dev-homepage-2026.md", "raw/articles/karpathy-guidelines-skill-2026.md" ], "url": "https://pyweb.dev/wiki/richard-feynman", "raw_markdown_url": "https://pyweb.dev/wiki/richard-feynman.md" }, { "id": "wiki:robert-c-martin", "slug": "robert-c-martin", "title": "Robert C. Martin (Uncle Bob)", "section": "entities", "type": "entity", "description": null, "created": "2026-08-25", "updated": "2026-08-25", "tags": [ "person", "educator" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/robert-c-martin", "raw_markdown_url": "https://pyweb.dev/wiki/robert-c-martin.md" }, { "id": "wiki:sabrina-haque", "slug": "sabrina-haque", "title": "Sabrina Haque", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/tests-agentic-pull-requests-2026.md" ], "url": "https://pyweb.dev/wiki/sabrina-haque", "raw_markdown_url": "https://pyweb.dev/wiki/sabrina-haque.md" }, { "id": "wiki:sarvesh-ingale", "slug": "sarvesh-ingale", "title": "Sarvesh Ingale", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/tests-agentic-pull-requests-2026.md" ], "url": "https://pyweb.dev/wiki/sarvesh-ingale", "raw_markdown_url": "https://pyweb.dev/wiki/sarvesh-ingale.md" }, { "id": "wiki:shashwat-saxena", "slug": "shashwat-saxena", "title": "Shashwat Saxena", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/adversarial-hacker-fixer-verifiers-2026.md" ], "url": "https://pyweb.dev/wiki/shashwat-saxena", "raw_markdown_url": "https://pyweb.dev/wiki/shashwat-saxena.md" }, { "id": "wiki:shazibul-islam-shamim", "slug": "shazibul-islam-shamim", "title": "Shazibul Islam Shamim", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/code-review-agents-empirical-study-2026.md" ], "url": "https://pyweb.dev/wiki/shazibul-islam-shamim", "raw_markdown_url": "https://pyweb.dev/wiki/shazibul-islam-shamim.md" }, { "id": "wiki:shopify", "slug": "shopify", "title": "Shopify", "section": "entities", "type": "entity", "description": "E-commerce platform company conducting autonomous agent optimization experiments.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "company", "agents", "evaluation" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md" ], "url": "https://pyweb.dev/wiki/shopify", "raw_markdown_url": "https://pyweb.dev/wiki/shopify.md" }, { "id": "wiki:shota-sawada", "slug": "shota-sawada", "title": "Shota Sawada", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/agent-generated-code-maintenance-2026.md" ], "url": "https://pyweb.dev/wiki/shota-sawada", "raw_markdown_url": "https://pyweb.dev/wiki/shota-sawada.md" }, { "id": "wiki:shreya-shankar", "slug": "shreya-shankar", "title": "Shreya Shankar", "section": "entities", "type": "entity", "description": "Computer science researcher at UC Berkeley focusing on data management, ML systems, and active-learning tooling for LLM error analysis and evaluation.", "created": "2026-08-22", "updated": "2026-08-22", "tags": [ "person", "educator", "evaluation" ], "sources": [ "raw/articles/parlance-labs-do-automated-evals-work-2026.md", "raw/articles/hamel-ai-product-engineering-notes-2026.md" ], "url": "https://pyweb.dev/wiki/shreya-shankar", "raw_markdown_url": "https://pyweb.dev/wiki/shreya-shankar.md" }, { "id": "wiki:sida-peng", "slug": "sida-peng", "title": "Sida Peng", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/github-copilot-productivity-experiment-2023.md" ], "url": "https://pyweb.dev/wiki/sida-peng", "raw_markdown_url": "https://pyweb.dev/wiki/sida-peng.md" }, { "id": "wiki:simon-willison", "slug": "simon-willison", "title": "Simon Willison", "section": "entities", "type": "entity", "description": "Software engineer, creator of Datasette, co-creator of Django, and prominent authority on LLM tooling, evals, and agentic engineering patterns.", "created": "2026-08-22", "updated": "2026-08-27", "tags": [ "person", "authority", "workflow" ], "sources": [], "url": "https://pyweb.dev/wiki/simon-willison", "raw_markdown_url": "https://pyweb.dev/wiki/simon-willison.md" }, { "id": "wiki:steve-freeman", "slug": "steve-freeman", "title": "Steve Freeman", "section": "entities", "type": "entity", "description": null, "created": "2026-08-25", "updated": "2026-08-25", "tags": [ "person", "educator" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/steve-freeman", "raw_markdown_url": "https://pyweb.dev/wiki/steve-freeman.md" }, { "id": "wiki:stripe", "slug": "stripe", "title": "Stripe", "section": "entities", "type": "entity", "description": "Financial infrastructure platform conducting benchmark research on autonomous coding agents building production payment integrations.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "organization", "evaluation", "benchmarks" ], "sources": [], "url": "https://pyweb.dev/wiki/stripe", "raw_markdown_url": "https://pyweb.dev/wiki/stripe.md" }, { "id": "wiki:tatsuya-shirai", "slug": "tatsuya-shirai", "title": "Tatsuya Shirai", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/agent-generated-code-maintenance-2026.md" ], "url": "https://pyweb.dev/wiki/tatsuya-shirai", "raw_markdown_url": "https://pyweb.dev/wiki/tatsuya-shirai.md" }, { "id": "wiki:tessl", "slug": "tessl", "title": "Tessl", "section": "entities", "type": "entity", "description": "AI software development company researching developer platforms, agentic software engineering benchmarks, and system harness architectures.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "company", "evaluation" ], "sources": [ "raw/articles/tessl-coding-benchmarks-misaligned-system-harness-2026.md" ], "url": "https://pyweb.dev/wiki/tessl", "raw_markdown_url": "https://pyweb.dev/wiki/tessl.md" }, { "id": "wiki:tobias-lutke", "slug": "tobias-lutke", "title": "Tobias Lütke", "section": "entities", "type": "entity", "description": "Shopify CEO who conducted autonomous agent optimization of Liquid template engine.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "person", "agents", "evaluation" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md" ], "url": "https://pyweb.dev/wiki/tobias-lutke", "raw_markdown_url": "https://pyweb.dev/wiki/tobias-lutke.md" }, { "id": "wiki:trygve-reenskaug", "slug": "trygve-reenskaug", "title": "Trygve Reenskaug", "section": "entities", "type": "entity", "description": null, "created": "2026-08-25", "updated": "2026-08-25", "tags": [ "person", "educator" ], "sources": [ "raw/articles/uncle-bob-clean-architecture-2012.md" ], "url": "https://pyweb.dev/wiki/trygve-reenskaug", "raw_markdown_url": "https://pyweb.dev/wiki/trygve-reenskaug.md" }, { "id": "wiki:tue-le", "slug": "tue-le", "title": "Tue Le", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/swe-evo-long-horizon-2026.md" ], "url": "https://pyweb.dev/wiki/tue-le", "raw_markdown_url": "https://pyweb.dev/wiki/tue-le.md" }, { "id": "wiki:vercel", "slug": "vercel", "title": "Vercel", "section": "entities", "type": "entity", "description": "Frontend platform company; creator of the AI SDK, a provider-neutral TypeScript interface for LLM generation, streaming, and tool calling.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [ "company", "llm-infrastructure" ], "sources": [ "raw/aihero-video/M02v00KLiYejPc55vWKBI6GETh6NM7Frcewj2i00q1oTyo.md", "raw/aihero-video/pEqcLrdb41402x028ndrEq2h24A51RkYC01yzqpfG4QJKo.md", "raw/aihero-video/cA6c02ZOSu7MxDK8I9z02J008OS3fwc01LkxNEiZW61DMhg.md" ], "url": "https://pyweb.dev/wiki/vercel", "raw_markdown_url": "https://pyweb.dev/wiki/vercel.md" }, { "id": "wiki:vinicius-carvalho-lopes", "slug": "vinicius-carvalho-lopes", "title": "Vinicius Carvalho Lopes", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/security-agentic-pull-requests-2026.md" ], "url": "https://pyweb.dev/wiki/vinicius-carvalho-lopes", "raw_markdown_url": "https://pyweb.dev/wiki/vinicius-carvalho-lopes.md" }, { "id": "wiki:viv-trivedy", "slug": "viv-trivedy", "title": "Viv Trivedy", "section": "entities", "type": "entity", "description": "Practitioner credited by Addy Osmani with naming harness engineering and articulating the model-plus-harness framing.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "person", "agents", "context-engineering" ], "sources": [ "https://addyosmani.com/blog/agent-harness-engineering/" ], "url": "https://pyweb.dev/wiki/viv-trivedy", "raw_markdown_url": "https://pyweb.dev/wiki/viv-trivedy.md" }, { "id": "wiki:wes-mckinney", "slug": "wes-mckinney", "title": "Wes McKinney", "section": "entities", "type": "entity", "description": "Creator of pandas, POSIT; pioneer of high-throughput agentic engineering harness workflows and automated post-commit review.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person", "workflow" ], "sources": [ "raw/articles/hugo-bowne-anderson-agentic-software-factory-2026.md" ], "url": "https://pyweb.dev/wiki/wes-mckinney", "raw_markdown_url": "https://pyweb.dev/wiki/wes-mckinney.md" }, { "id": "wiki:wilson-lin", "slug": "wilson-lin", "title": "Wilson Lin", "section": "entities", "type": "entity", "description": "Cursor researcher documenting planner-worker architectures for long-running autonomous coding.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "person", "agents", "workflow" ], "sources": [ "https://cursor.com/blog/scaling-agents" ], "url": "https://pyweb.dev/wiki/wilson-lin", "raw_markdown_url": "https://pyweb.dev/wiki/wilson-lin.md" }, { "id": "wiki:xinye-zhao", "slug": "xinye-zhao", "title": "Xinye Zhao", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/security-agentic-pull-requests-2026.md" ], "url": "https://pyweb.dev/wiki/xinye-zhao", "raw_markdown_url": "https://pyweb.dev/wiki/xinye-zhao.md" }, { "id": "wiki:yanjun-zhang", "slug": "yanjun-zhang", "title": "Yanjun Zhang", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/overeager-coding-agents-2026.md" ], "url": "https://pyweb.dev/wiki/yanjun-zhang", "raw_markdown_url": "https://pyweb.dev/wiki/yanjun-zhang.md" }, { "id": "wiki:yi-liu", "slug": "yi-liu", "title": "Yi Liu", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/overeager-coding-agents-2026.md" ], "url": "https://pyweb.dev/wiki/yi-liu", "raw_markdown_url": "https://pyweb.dev/wiki/yi-liu.md" }, { "id": "wiki:ying-zhang", "slug": "ying-zhang", "title": "Ying Zhang", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/overeager-coding-agents-2026.md" ], "url": "https://pyweb.dev/wiki/ying-zhang", "raw_markdown_url": "https://pyweb.dev/wiki/ying-zhang.md" }, { "id": "wiki:yubin-qu", "slug": "yubin-qu", "title": "Yubin Qu", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/overeager-coding-agents-2026.md" ], "url": "https://pyweb.dev/wiki/yubin-qu", "raw_markdown_url": "https://pyweb.dev/wiki/yubin-qu.md" }, { "id": "wiki:yuekang-li", "slug": "yuekang-li", "title": "Yuekang Li", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/overeager-coding-agents-2026.md" ], "url": "https://pyweb.dev/wiki/yuekang-li", "raw_markdown_url": "https://pyweb.dev/wiki/yuekang-li.md" }, { "id": "wiki:yutaro-kashiwa", "slug": "yutaro-kashiwa", "title": "Yutaro Kashiwa", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/agent-generated-code-maintenance-2026.md", "raw/papers/agentic-pull-requests-github-2026.md" ], "url": "https://pyweb.dev/wiki/yutaro-kashiwa", "raw_markdown_url": "https://pyweb.dev/wiki/yutaro-kashiwa.md" }, { "id": "wiki:ziqian-zhong", "slug": "ziqian-zhong", "title": "Ziqian Zhong", "section": "entities", "type": "entity", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "person" ], "sources": [ "raw/papers/adversarial-hacker-fixer-verifiers-2026.md" ], "url": "https://pyweb.dev/wiki/ziqian-zhong", "raw_markdown_url": "https://pyweb.dev/wiki/ziqian-zhong.md" }, { "id": "wiki:agentic-quality-evidence", "slug": "agentic-quality-evidence", "title": "Agentic Code Quality — Evidence Map", "section": "comparisons", "type": "comparison", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "comparison", "evaluation", "agents", "code-review", "security" ], "sources": [], "url": "https://pyweb.dev/wiki/agentic-quality-evidence", "raw_markdown_url": "https://pyweb.dev/wiki/agentic-quality-evidence.md" }, { "id": "wiki:agentic-code-quality-cycle-2-entity-accounting", "slug": "agentic-code-quality-cycle-2-entity-accounting", "title": "Agentic Code Quality Cycle 2 — Entity Accounting", "section": "queries", "type": "query", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "evaluation", "agents", "retrospective" ], "sources": [], "url": "https://pyweb.dev/wiki/agentic-code-quality-cycle-2-entity-accounting", "raw_markdown_url": "https://pyweb.dev/wiki/agentic-code-quality-cycle-2-entity-accounting.md" }, { "id": "wiki:agentic-code-quality-entity-accounting", "slug": "agentic-code-quality-entity-accounting", "title": "Agentic Code Quality Evidence — Entity Accounting", "section": "queries", "type": "query", "description": null, "created": "2026-08-27", "updated": "2026-08-27", "tags": [ "evaluation", "agents" ], "sources": [ "raw/papers/agent-generated-code-maintenance-2026.md", "raw/papers/agentic-pull-requests-github-2026.md", "raw/papers/swe-evo-long-horizon-2026.md", "raw/papers/security-agentic-pull-requests-2026.md", "raw/papers/aidev-dataset-2026.md", "raw/papers/autonomous-agent-contributions-wild-2026.md", "raw/papers/code-review-agents-empirical-study-2026.md", "raw/papers/tests-agentic-pull-requests-2026.md", "raw/papers/adversarial-hacker-fixer-verifiers-2026.md", "raw/papers/overeager-coding-agents-2026.md", "raw/papers/metr-developer-productivity-rct-2025.md", "raw/papers/github-copilot-productivity-experiment-2023.md" ], "url": "https://pyweb.dev/wiki/agentic-code-quality-entity-accounting", "raw_markdown_url": "https://pyweb.dev/wiki/agentic-code-quality-entity-accounting.md" }, { "id": "wiki:agentic-engineering-entity-accounting", "slug": "agentic-engineering-entity-accounting", "title": "Agentic Engineering Entity Accounting", "section": "queries", "type": "query", "description": "Entity disposition query documenting the 2026-08-24 ingestion of agentic engineering trends synthesis", "created": "2026-08-24", "updated": "2026-08-24", "tags": [ "knowledge-management", "retrospective" ], "sources": [ "raw/articles/agentic-engineering-trends-2026-synthesis.md" ], "url": "https://pyweb.dev/wiki/agentic-engineering-entity-accounting", "raw_markdown_url": "https://pyweb.dev/wiki/agentic-engineering-entity-accounting.md" }, { "id": "wiki:llm-wiki-ecosystem-analysis", "slug": "llm-wiki-ecosystem-analysis", "title": "LLM Wiki Ecosystem: Spec vs. Implementations", "section": "queries", "type": "query", "description": "Comparative query analyzing the LLM Wiki specification against real-world implementations, including this site.", "created": "2026-08-23", "updated": "2026-08-23", "tags": [ "knowledge-management", "comparison", "agents", "principle" ], "sources": [ "raw/articles/karpathy-wiki-ecosystem-analysis-2026.md" ], "url": "https://pyweb.dev/wiki/llm-wiki-ecosystem-analysis", "raw_markdown_url": "https://pyweb.dev/wiki/llm-wiki-ecosystem-analysis.md" }, { "id": "writing:clean-architecture-for-agent-harnesses", "slug": "clean-architecture-for-agent-harnesses", "title": "Clean Architecture for Agent Harnesses", "section": "writing", "type": "post", "description": "How Uncle Bob's 2012 Dependency Rule and boundary isolation principles solve the durability, containment, and testability crises in modern AI agent harnesses.", "created": "2026-08-25", "updated": "2026-08-25", "tags": [], "sources": [], "url": "https://pyweb.dev/writing/clean-architecture-for-agent-harnesses", "raw_markdown_url": "https://pyweb.dev/writing/clean-architecture-for-agent-harnesses.md" }, { "id": "writing:hello-world", "slug": "hello-world", "title": "Hello world", "section": "writing", "type": "post", "description": "The first post on pyweb.dev", "created": "2026-08-22", "updated": "2026-08-22", "tags": [], "sources": [], "url": "https://pyweb.dev/writing/hello-world", "raw_markdown_url": "https://pyweb.dev/writing/hello-world.md" }, { "id": "writing:skills-native-evaluation-agent-adversarial-training", "slug": "skills-native-evaluation-agent-adversarial-training", "title": "Skills-Native Evaluation and Agent Adversarial Training", "section": "writing", "type": "post", "description": "How evaluation methodology shipped as installable skills and GAN-inspired generator-evaluator loops are advancing AI agent reliability beyond prompt tweaks.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [], "sources": [], "url": "https://pyweb.dev/writing/skills-native-evaluation-agent-adversarial-training", "raw_markdown_url": "https://pyweb.dev/writing/skills-native-evaluation-agent-adversarial-training.md" }, { "id": "writing:building-effective-agentic-workflows", "slug": "building-effective-agentic-workflows", "title": "Building Effective Agentic Workflows", "section": "writing", "type": "post", "description": "A practitioner's architectural guide to building reliable AI coding agents: avoiding context rot, operating in the smart zone, and enforcing tight engineering loops.", "created": "2026-08-22", "updated": "2026-08-22", "tags": [], "sources": [], "url": "https://pyweb.dev/writing/building-effective-agentic-workflows", "raw_markdown_url": "https://pyweb.dev/writing/building-effective-agentic-workflows.md" }, { "id": "writing:agentic-engineering-curriculum", "slug": "agentic-engineering-curriculum", "title": "The Agentic Engineering Curriculum", "section": "writing", "type": "post", "description": "A structured course on AI engineering and agentic patterns, distilled from the wiki: foundations, context, evals, verification, harnesses, and the software factory.", "created": "2026-08-30", "updated": "2026-08-30", "tags": [], "sources": [], "url": "https://pyweb.dev/writing/agentic-engineering-curriculum", "raw_markdown_url": "https://pyweb.dev/writing/agentic-engineering-curriculum.md" }, { "id": "writing:the-agent-as-a-virtual-os-codex-harness-architecture", "slug": "the-agent-as-a-virtual-os-codex-harness-architecture", "title": "The Agent as a Virtual OS: Inside the Codex Harness Architecture", "section": "writing", "type": "post", "description": "Dissecting OpenAI's Codex harness: JSON-RPC app-server decoupling, multi-platform OS sandboxing, bounded context streams, and the lessons of production agent design.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [], "sources": [], "url": "https://pyweb.dev/writing/the-agent-as-a-virtual-os-codex-harness-architecture", "raw_markdown_url": "https://pyweb.dev/writing/the-agent-as-a-virtual-os-codex-harness-architecture.md" }, { "id": "writing:five-debts-of-agentic-engineering", "slug": "five-debts-of-agentic-engineering", "title": "The Five Debts of Agentic Engineering", "section": "writing", "type": "post", "description": "Why probabilistic coding generators accumulate intent, semantic, verification, architecture, and authorization debt—and how risk-conditioned systems keep autonomous loops releasable.", "created": "2026-08-27", "updated": "2026-08-27", "tags": [], "sources": [], "url": "https://pyweb.dev/writing/five-debts-of-agentic-engineering", "raw_markdown_url": "https://pyweb.dev/writing/five-debts-of-agentic-engineering.md" }, { "id": "writing:loop-and-graph-engineering", "slug": "loop-and-graph-engineering", "title": "Loop and Graph Engineering: The Dual Topologies of Agentic Systems", "section": "writing", "type": "post", "description": "Why single-agent prompt loops degrade past the smart zone, and how graph orchestration provides the structural partition needed for production AI systems.", "created": "2026-08-24", "updated": "2026-08-24", "tags": [], "sources": [], "url": "https://pyweb.dev/writing/loop-and-graph-engineering", "raw_markdown_url": "https://pyweb.dev/writing/loop-and-graph-engineering.md" }, { "id": "writing:the-linter-is-the-cheapest-adult-in-the-room", "slug": "the-linter-is-the-cheapest-adult-in-the-room", "title": "The Linter Is the Cheapest Adult in the Room", "section": "writing", "type": "post", "description": "Why Rust-speed, error-only lint gates like Oxlint are the Tier 1 backpressure layer that keeps autonomous coding loops honest — with the failure modes they mechanically close.", "created": "2026-08-28", "updated": "2026-08-28", "tags": [], "sources": [], "url": "https://pyweb.dev/writing/the-linter-is-the-cheapest-adult-in-the-room", "raw_markdown_url": "https://pyweb.dev/writing/the-linter-is-the-cheapest-adult-in-the-room.md" } ], "edges": [ { "source": "wiki:ag-ui-protocol", "target": "wiki:copilotkit", "type": "references", "note": "in partnership with ecosystem frameworks (LangChain, CrewAI, Microsoft Agent Framework, AWS Bedrock AgentCore), AG-UI defines the frontend i" }, { "source": "wiki:ag-ui-protocol", "target": "wiki:anthropic", "type": "references", "note": "| Standardizes tool definitions, context injection, and resource prompts. |" }, { "source": "wiki:ag-ui-protocol", "target": "wiki:agent-native-infrastructure", "type": "references", "note": "underlying platform and runtime tier" }, { "source": "wiki:ag-ui-protocol", "target": "wiki:claude-managed-agents", "type": "references", "note": "cloud-hosted agent loop implementing AG-UI adapters" }, { "source": "wiki:agent-containment-and-blast-radius", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:agent-containment-and-blast-radius", "target": "wiki:multi-agent-orchestration", "type": "references", "note": null }, { "source": "wiki:agent-containment-and-blast-radius", "target": "wiki:subagents-and-context-management", "type": "references", "note": null }, { "source": "wiki:agent-containment-and-blast-radius", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:agent-containment-and-blast-radius", "target": "wiki:anthropic", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:prompt-bloat", "type": "references", "note": "and degrades reasoning sharpness in the smart-zone. Harnesses expose compact tool/skill indexes (~50 characters per trigger) and hydrate ful" }, { "source": "wiki:agent-harness-engineering", "target": "wiki:red-green-tdd", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:context-engineering", "type": "references", "note": "), allowing agents to query precise interface definitions and cross-references on demand." }, { "source": "wiki:agent-harness-engineering", "target": "wiki:drew-breunig", "type": "references", "note": "marks the economic turn: prior to Fable it felt silly to invest heavily in your coding harness or context strategies, because \"A new model w" }, { "source": "wiki:agent-harness-engineering", "target": "wiki:hamel-husain", "type": "references", "note": "adds that a large portion of the harness is data science: beyond tests and specifications, production harnesses include an observability sta" }, { "source": "wiki:agent-harness-engineering", "target": "wiki:agentic-code-quality", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:agentic-software-factory", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:agentic-engineering-entity-accounting", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:clean-architecture", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:dependency-rule", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:codex-harness-architecture", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:agent-containment-and-blast-radius", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:deepseek-harness", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:cordis-framework", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:agent-native-infrastructure", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:progressive-disclosure", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:subagents-and-context-management", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:smart-zone", "type": "references", "note": null }, { "source": "wiki:agent-harness-engineering", "target": "wiki:tdd-with-agents", "type": "references", "note": null }, { "source": "wiki:agent-native-infrastructure", "target": "wiki:ag-ui-protocol", "type": "references", "note": "for event-driven frontend streaming and generative UI, MCP for tool connections, and A2A for distributed multi-agent delegation. ^[raw/artic" }, { "source": "wiki:agent-native-infrastructure", "target": "wiki:claude-managed-agents", "type": "references", "note": "separate reasoning engines from isolated Linux microVM sandboxes, persisting append-only event trees and enabling human-in-the-loop permissi" }, { "source": "wiki:agent-native-infrastructure", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:agent-native-infrastructure", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:agent-native-infrastructure", "target": "wiki:progressive-disclosure", "type": "references", "note": null }, { "source": "wiki:agent-native-infrastructure", "target": "wiki:llm-wiki-pattern", "type": "references", "note": null }, { "source": "wiki:agent-native-infrastructure", "target": "wiki:subagents-and-context-management", "type": "references", "note": null }, { "source": "wiki:agentic-code-quality", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": "and eval-driven-development, empirical research reveals distinct failure modes: test-oracle defects, reward hacking, scope expansion, noisy " }, { "source": "wiki:agentic-code-quality", "target": "wiki:red-green-tdd", "type": "references", "note": "; evaluate those tests independently." }, { "source": "wiki:agentic-code-quality", "target": "wiki:deterministic-lint-gates", "type": "references", "note": "for the error-only gate pattern); tsc --noEmit --incremental for type compatibility; changed Vitest/Jest unit tests.^[raw/articles/oxlint-ty" }, { "source": "wiki:agentic-code-quality", "target": "wiki:eval-driven-development", "type": "references", "note": null }, { "source": "wiki:agentic-code-quality", "target": "wiki:five-debts-of-agentic-engineering", "type": "references", "note": "generative debt modes and control mappings" }, { "source": "wiki:agentic-code-quality", "target": "wiki:releasable-patch-rate", "type": "references", "note": "north-star factory metric" }, { "source": "wiki:agentic-code-quality", "target": "wiki:constraint-layering", "type": "references", "note": "allocating controls across prompt, tools, and sandboxes" }, { "source": "wiki:agentic-code-quality", "target": "wiki:skill-treatment-effect", "type": "references", "note": "empirical evaluation of procedural skills" }, { "source": "wiki:agentic-code-quality", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "empirical evidence and contradictions" }, { "source": "wiki:agentic-code-quality", "target": "wiki:agentic-software-factory", "type": "references", "note": "operating model" }, { "source": "wiki:agentic-code-quality", "target": "wiki:agent-containment-and-blast-radius", "type": "references", "note": "authorization and damage bounds" }, { "source": "wiki:agentic-code-quality", "target": "wiki:designing-for-verifiability", "type": "references", "note": "inspectable product contracts" }, { "source": "wiki:agentic-code-quality", "target": "wiki:agentic-code-quality-entity-accounting", "type": "references", "note": "cycle 1 source-author dispositions" }, { "source": "wiki:agentic-code-quality", "target": "wiki:agentic-code-quality-cycle-2-entity-accounting", "type": "references", "note": "cycle 2 source-author dispositions" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:simon-willison", "type": "references", "note": ", it distinguishes disciplined engineering with feedback loops from unconstrained \"vibe coding\".^[raw/articles/simon-willison-agentic-engine" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:kent-beck", "type": "references", "note": "identifies TDD as the fundamental governor for coding agents (\"the unpredictable genie\").^[raw/articles/kent-beck-gergely-orosz-tdd-ai-agent" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:boris-cherny", "type": "references", "note": "in Claude Code's internal harness.^[raw/articles/boris-cherny-how-boris-uses-claude-code-2026.md]" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:software-engineering-fundamentals-for-agents", "type": "references", "note": "the 5 foundational pillars required to steer agentic code" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:five-debts-of-agentic-engineering", "type": "references", "note": "generative debt modes prevented by these patterns" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:andrew-ng", "type": "references", "note": "author of AI Engineering Skills Map" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:releasable-patch-rate", "type": "references", "note": "measuring complete patch delivery" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:agentic-code-quality", "type": "references", "note": "multi-tier quality controls" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:red-green-tdd", "type": "references", "note": "test-driven cycle" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:agent-harness-engineering", "type": "references", "note": "harness design" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:git-for-agentic-workflows", "type": "references", "note": "version control discipline" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:hoard-and-recombine", "type": "references", "note": "collecting verified code references" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:github", "type": "references", "note": "developer platform & spec-driven toolkit" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:evals-skills", "type": "references", "note": "evaluation tooling" }, { "source": "wiki:agentic-engineering-patterns", "target": "wiki:martin-fowler", "type": "references", "note": "comprehension loop" }, { "source": "wiki:agentic-manual-testing", "target": "wiki:simon-willison", "type": "references", "note": null }, { "source": "wiki:agentic-manual-testing", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:agentic-manual-testing", "target": "wiki:red-green-tdd", "type": "references", "note": null }, { "source": "wiki:agentic-manual-testing", "target": "wiki:tdd-with-agents", "type": "references", "note": null }, { "source": "wiki:agentic-manual-testing", "target": "wiki:karpathy-four-guidelines", "type": "references", "note": null }, { "source": "wiki:agentic-manual-testing", "target": "wiki:closed-loop-agent-improvement", "type": "references", "note": null }, { "source": "wiki:agentic-manual-testing", "target": "wiki:automated-eval-engineering", "type": "references", "note": null }, { "source": "wiki:agentic-software-factory", "target": "wiki:agentic-code-quality", "type": "references", "note": null }, { "source": "wiki:agentic-software-factory", "target": "wiki:agent-harness-engineering", "type": "references", "note": "operating infrastructure and runtime isolation" }, { "source": "wiki:agentic-software-factory", "target": "wiki:multi-agent-orchestration", "type": "references", "note": "coordinator and worker agent hierarchies" }, { "source": "wiki:agentic-software-factory", "target": "wiki:conformance-suites-as-fitness-functions", "type": "references", "note": "test suites as objective factory fitness functions" }, { "source": "wiki:agentic-software-factory", "target": "wiki:wes-mckinney", "type": "references", "note": "factory practitioner, post-commit review systems" }, { "source": "wiki:agentic-software-factory", "target": "wiki:addy-osmani", "type": "references", "note": "constraint-driven quality in software factories" }, { "source": "wiki:agentic-software-factory", "target": "wiki:tessl", "type": "references", "note": "system harness benchmarks and NS2 orchestration" }, { "source": "wiki:agentic-vulnerability-lifecycle", "target": "wiki:anil-madhavapeddy", "type": "references", "note": "(professor of computer science at Cambridge and core maintainer of the OCaml compiler) reported that security issues in OCaml projects exper" }, { "source": "wiki:agentic-vulnerability-lifecycle", "target": "wiki:nick-craig-wood", "type": "references", "note": "(maintainer of rclone) reported receiving over 40 security disclosures in a single month, compared to roughly 20 disclosures across the firs" }, { "source": "wiki:agentic-vulnerability-lifecycle", "target": "wiki:agent-containment-and-blast-radius", "type": "references", "note": null }, { "source": "wiki:agentic-vulnerability-lifecycle", "target": "wiki:conformance-suites-as-fitness-functions", "type": "references", "note": null }, { "source": "wiki:agentic-vulnerability-lifecycle", "target": "wiki:constraint-layering", "type": "references", "note": null }, { "source": "wiki:agentic-vulnerability-lifecycle", "target": "wiki:simon-willison", "type": "references", "note": "analysis of agent security boundaries" }, { "source": "wiki:agents-md-spec", "target": "wiki:context-engineering", "type": "references", "note": ", prompt-bloat, progressive-disclosure, ai-coding-taxonomy." }, { "source": "wiki:agents-vs-workflows", "target": "wiki:multi-agent-orchestration", "type": "references", "note": null }, { "source": "wiki:agents-vs-workflows", "target": "wiki:generator-evaluator-loop", "type": "references", "note": null }, { "source": "wiki:agents-vs-workflows", "target": "wiki:tool-calling-loop", "type": "references", "note": ".^[raw/aihero/building-effective-agents.md]" }, { "source": "wiki:agents-vs-workflows", "target": "wiki:model-provider-abstraction", "type": "references", "note": null }, { "source": "wiki:ai-coding-taxonomy", "target": "wiki:matt-pocock", "type": "references", "note": "'s AI Hero curriculum." }, { "source": "wiki:ai-coding-taxonomy", "target": "wiki:agent-harness-engineering", "type": "references", "note": "surrounds the model with tools, system prompts, context-window management, permissions, and hooks." }, { "source": "wiki:ai-coding-taxonomy", "target": "wiki:smart-zone", "type": "references", "note": "early in a session versus the sloppier \"dumb zone\" later in extended sessions." }, { "source": "wiki:ai-coding-taxonomy", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:ai-coding-taxonomy", "target": "wiki:context-rot", "type": "references", "note": null }, { "source": "wiki:ai-coding-taxonomy", "target": "wiki:agents-md-spec", "type": "references", "note": null }, { "source": "wiki:ai-coding-taxonomy", "target": "wiki:handoff-artifacts", "type": "references", "note": null }, { "source": "wiki:ai-coding-taxonomy", "target": "wiki:progressive-disclosure", "type": "references", "note": null }, { "source": "wiki:ai-engineer-role", "target": "wiki:eval-taxonomy", "type": "references", "note": ", the Vibes-Only Trough to Data-Driven Slope journey). The role's daily work spans llm-message-protocol mechanics, agents-vs-workflows archi" }, { "source": "wiki:automated-eval-engineering", "target": "wiki:error-analysis-and-evals", "type": "references", "note": null }, { "source": "wiki:automated-eval-engineering", "target": "wiki:closed-loop-agent-improvement", "type": "references", "note": null }, { "source": "wiki:automated-eval-engineering", "target": "wiki:agentic-manual-testing", "type": "references", "note": null }, { "source": "wiki:automated-eval-engineering", "target": "wiki:tdd-with-agents", "type": "references", "note": null }, { "source": "wiki:automated-eval-engineering", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:build-from-scratch-pedagogy", "target": "wiki:andrej-karpathy", "type": "references", "note": "'s teaching move: build the minimal version from scratch to understand" }, { "source": "wiki:build-from-scratch-pedagogy", "target": "wiki:richard-feynman", "type": "references", "note": "'s last blackboard: \"What I cannot create, I do not understand.\"" }, { "source": "wiki:build-from-scratch-pedagogy", "target": "wiki:feynman-technique", "type": "references", "note": null }, { "source": "wiki:build-from-scratch-pedagogy", "target": "wiki:tracer-bullets", "type": "references", "note": "at the learning level: the minimal build is the tracer bullet" }, { "source": "wiki:build-from-scratch-pedagogy", "target": "wiki:karpathy-four-guidelines", "type": "references", "note": "#2 (simplicity first)" }, { "source": "wiki:claude-managed-agents", "target": "wiki:anthropic", "type": "references", "note": "'s cloud-hosted infrastructure platform for deploying autonomous, long-running agent workflows. CMA decouples agent reasoning orchestration " }, { "source": "wiki:claude-managed-agents", "target": "wiki:ag-ui-protocol", "type": "references", "note": "and client libraries (copilotkit, assistant-ui), CMA sessions map 1:1 to user chat threads:" }, { "source": "wiki:claude-managed-agents", "target": "wiki:agent-native-infrastructure", "type": "references", "note": "underlying compute paradigm" }, { "source": "wiki:claude-managed-agents", "target": "wiki:copilotkit", "type": "references", "note": "integration ecosystem partner" }, { "source": "wiki:clean-architecture", "target": "wiki:robert-c-martin", "type": "references", "note": "that integrates multiple layered architectural approaches into a unified system design philosophy. Clean Architecture organizes systems into" }, { "source": "wiki:clean-architecture", "target": "wiki:dependency-inversion-principle", "type": "references", "note": "to maintain the dependency rule while allowing necessary data flow. Interfaces in inner circles are implemented by outer circles, using dyna" }, { "source": "wiki:clean-architecture", "target": "wiki:hexagonal-architecture", "type": "references", "note": "(Ports and Adapters) by alistair-cockburn" }, { "source": "wiki:clean-architecture", "target": "wiki:onion-architecture", "type": "references", "note": "by jeffrey-palermo" }, { "source": "wiki:clean-architecture", "target": "wiki:james-coplien", "type": "references", "note": "and trygve-reenskaug" }, { "source": "wiki:clean-architecture", "target": "wiki:ivar-jacobson", "type": "references", "note": null }, { "source": "wiki:clean-architecture", "target": "wiki:dependency-rule", "type": "references", "note": null }, { "source": "wiki:clean-architecture", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:clean-architecture", "target": "wiki:cordis-framework", "type": "references", "note": null }, { "source": "wiki:clean-architecture", "target": "wiki:deepseek-harness", "type": "references", "note": null }, { "source": "wiki:closed-loop-agent-improvement", "target": "wiki:error-analysis-and-evals", "type": "references", "note": null }, { "source": "wiki:closed-loop-agent-improvement", "target": "wiki:automated-eval-engineering", "type": "references", "note": null }, { "source": "wiki:closed-loop-agent-improvement", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:closed-loop-agent-improvement", "target": "wiki:agentic-manual-testing", "type": "references", "note": null }, { "source": "wiki:closed-loop-agent-improvement", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:codex-harness-architecture", "target": "wiki:openai", "type": "references", "note": "'s open-source coding agent repository (openai/codex). Built in Rust (codex-rs), it exemplifies production agent-harness-engineering by appl" }, { "source": "wiki:codex-harness-architecture", "target": "wiki:smart-zone", "type": "references", "note": "against context-rot." }, { "source": "wiki:codex-harness-architecture", "target": "wiki:agent-harness-engineering", "type": "references", "note": "broader discipline of agent runtime infrastructure" }, { "source": "wiki:codex-harness-architecture", "target": "wiki:clean-architecture", "type": "references", "note": "inward dependency boundaries" }, { "source": "wiki:codex-harness-architecture", "target": "wiki:hexagonal-architecture", "type": "references", "note": "ports and adapters isolation" }, { "source": "wiki:codex-harness-architecture", "target": "wiki:deepseek-harness", "type": "references", "note": "microkernel plugin alternative for agent harnesses" }, { "source": "wiki:codex-harness-architecture", "target": "wiki:agent-containment-and-blast-radius", "type": "references", "note": "containment and egress security" }, { "source": "wiki:codex-harness-architecture", "target": "wiki:context-rot", "type": "references", "note": "degradation from unbounded token accumulation" }, { "source": "wiki:cognitive-debt-and-walkthroughs", "target": "wiki:editorial-diagrams-and-visual-explanations", "type": "references", "note": ") authored by cathryn-lavery to visualize flows, decision trees, and system state with strict density and signal discipline." }, { "source": "wiki:cognitive-debt-and-walkthroughs", "target": "wiki:simon-willison", "type": "references", "note": null }, { "source": "wiki:cognitive-debt-and-walkthroughs", "target": "wiki:cathryn-lavery", "type": "references", "note": null }, { "source": "wiki:cognitive-debt-and-walkthroughs", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:cognitive-debt-and-walkthroughs", "target": "wiki:feynman-technique", "type": "references", "note": null }, { "source": "wiki:cognitive-debt-and-walkthroughs", "target": "wiki:build-from-scratch-pedagogy", "type": "references", "note": null }, { "source": "wiki:conformance-suites-as-fitness-functions", "target": "wiki:red-green-tdd", "type": "references", "note": null }, { "source": "wiki:conformance-suites-as-fitness-functions", "target": "wiki:tdd-with-agents", "type": "references", "note": null }, { "source": "wiki:conformance-suites-as-fitness-functions", "target": "wiki:automated-eval-engineering", "type": "references", "note": null }, { "source": "wiki:conformance-suites-as-fitness-functions", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:conformance-suites-as-fitness-functions", "target": "wiki:multi-agent-orchestration", "type": "references", "note": null }, { "source": "wiki:constraint-layering", "target": "wiki:deterministic-lint-gates", "type": "references", "note": "), formatting, import boundaries | Fragile regex hooks that block valid edits |" }, { "source": "wiki:constraint-layering", "target": "wiki:agent-containment-and-blast-radius", "type": "references", "note": "Restricting agent execution privileges." }, { "source": "wiki:constraint-layering", "target": "wiki:agent-harness-engineering", "type": "references", "note": "Harness architecture and layered runtime controls." }, { "source": "wiki:constraint-layering", "target": "wiki:progressive-disclosure", "type": "references", "note": "Dynamic context loading based on execution phase." }, { "source": "wiki:constraint-layering", "target": "wiki:five-debts-of-agentic-engineering", "type": "references", "note": "Structural debts prevented by proper constraint layering." }, { "source": "wiki:context-budget-audit", "target": "wiki:prompt-bloat", "type": "references", "note": "remediation with instrumentation." }, { "source": "wiki:context-budget-audit", "target": "wiki:progressive-disclosure", "type": "references", "note": "(load skills on demand) and why tool-calling-loop carries an under-6-tools budget. Feedback-loop infrastructure (typecheck, tests, pre-commi" }, { "source": "wiki:context-engineering", "target": "wiki:matt-pocock", "type": "references", "note": "'s framing: context is the game. AGENTS.md, CONTEXT.md, feedback loops," }, { "source": "wiki:context-engineering", "target": "wiki:agents-md-spec", "type": "references", "note": null }, { "source": "wiki:context-engineering", "target": "wiki:progressive-disclosure", "type": "references", "note": null }, { "source": "wiki:context-engineering", "target": "wiki:editorial-diagrams-and-visual-explanations", "type": "references", "note": ") that provide structured multi-hop context without prompt bloat." }, { "source": "wiki:context-engineering", "target": "wiki:andrej-karpathy", "type": "references", "note": "'s llm-wiki-pattern is the same principle at the knowledge level:" }, { "source": "wiki:context-engineering", "target": "wiki:context-budget-audit", "type": "references", "note": "the measured, instrumented practice of this principle at the harness layer." }, { "source": "wiki:context-engineering", "target": "wiki:llm-wiki-pattern", "type": "references", "note": ", grilling-doctrine, idea-to-ship-flow, error-analysis-and-evals, hamel-husain, progressive-disclosure." }, { "source": "wiki:context-rot", "target": "wiki:smart-zone", "type": "references", "note": ", handoff-artifacts, context-engineering, prompt-bloat, subagents-and-context-management, ai-coding-taxonomy." }, { "source": "wiki:cordis-framework", "target": "wiki:deepseek-harness", "type": "references", "note": ". It provides modular lifecycle management, service containers, typed event buses, and reversible side-effects for agent runtimes." }, { "source": "wiki:cordis-framework", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:cordis-framework", "target": "wiki:agent-native-infrastructure", "type": "references", "note": null }, { "source": "wiki:cordis-framework", "target": "wiki:deepseek", "type": "references", "note": null }, { "source": "wiki:deepseek-harness", "target": "wiki:deepseek", "type": "references", "note": "built around the architectural thesis Agent = Model + Harness. It provides a modular, traceable execution harness designed to keep autonomou" }, { "source": "wiki:deepseek-harness", "target": "wiki:cordis-framework", "type": "references", "note": ", delegating all functional capabilities into plugins that register typed services:" }, { "source": "wiki:deepseek-harness", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:deepseek-harness", "target": "wiki:agent-native-infrastructure", "type": "references", "note": null }, { "source": "wiki:deepseek-harness", "target": "wiki:subagents-and-context-management", "type": "references", "note": null }, { "source": "wiki:deepseek-harness", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:dependency-inversion-principle", "target": "wiki:clean-architecture", "type": "references", "note": "'s dependency-rule to work in practice by using dynamic polymorphism to create source code dependencies that oppose the flow of control. Thi" }, { "source": "wiki:dependency-rule", "target": "wiki:clean-architecture", "type": "references", "note": "that governs how software components can depend on each other. The rule states that source code dependencies can only point inwards toward h" }, { "source": "wiki:dependency-rule", "target": "wiki:dependency-inversion-principle", "type": "references", "note": "resolves the contradiction:" }, { "source": "wiki:designing-for-verifiability", "target": "wiki:hamel-husain", "type": "references", "note": "argues that the most common objection to evals — \"our product is hard to eval\" — is a product smell. Artifacts that are hard for the builder" }, { "source": "wiki:designing-for-verifiability", "target": "wiki:agent-harness-engineering", "type": "references", "note": "). Both reduce to the same move: make correctness checkable by construction, rather than asserting it. It also makes evals tractable — check" }, { "source": "wiki:designing-for-verifiability", "target": "wiki:error-analysis-and-evals", "type": "references", "note": null }, { "source": "wiki:designing-for-verifiability", "target": "wiki:automated-eval-engineering", "type": "references", "note": null }, { "source": "wiki:designing-for-verifiability", "target": "wiki:agentic-manual-testing", "type": "references", "note": null }, { "source": "wiki:designing-for-verifiability", "target": "wiki:tdd-with-agents", "type": "references", "note": null }, { "source": "wiki:deterministic-lint-gates", "target": "wiki:constraint-layering", "type": "references", "note": "'s \"script the mechanical\" maxim inside agentic-code-quality." }, { "source": "wiki:deterministic-lint-gates", "target": "wiki:christoph-nakazawa", "type": "references", "note": ") is an opinionated preset whose principles map directly onto agent-loop failure modes:^[raw/articles/nkzw-oxlint-config-2026.md]" }, { "source": "wiki:deterministic-lint-gates", "target": "wiki:agentic-code-quality", "type": "references", "note": null }, { "source": "wiki:deterministic-lint-gates", "target": "wiki:multi-agent-orchestration", "type": "references", "note": ", not aesthetics." }, { "source": "wiki:deterministic-lint-gates", "target": "wiki:five-debts-of-agentic-engineering", "type": "references", "note": "verification debt closed by mechanical gates" }, { "source": "wiki:deterministic-lint-gates", "target": "wiki:releasable-patch-rate", "type": "references", "note": "the factory metric fast gates protect" }, { "source": "wiki:deterministic-lint-gates", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": "bounded fix loops and execution budgets" }, { "source": "wiki:editorial-diagrams-and-visual-explanations", "target": "wiki:cathryn-lavery", "type": "references", "note": "in the Diagram Design specification, the approach bridges technical architecture representation and cognitive-debt-and-walkthroughs." }, { "source": "wiki:editorial-diagrams-and-visual-explanations", "target": "wiki:cognitive-debt-and-walkthroughs", "type": "references", "note": null }, { "source": "wiki:editorial-diagrams-and-visual-explanations", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:editorial-diagrams-and-visual-explanations", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:editorial-diagrams-and-visual-explanations", "target": "wiki:progressive-disclosure", "type": "references", "note": null }, { "source": "wiki:editorial-diagrams-and-visual-explanations", "target": "wiki:build-from-scratch-pedagogy", "type": "references", "note": null }, { "source": "wiki:error-analysis-and-evals", "target": "wiki:hamel-husain", "type": "references", "note": "and shreya-shankar, it forms the foundational requirement for building defensible AI applications." }, { "source": "wiki:error-analysis-and-evals", "target": "wiki:shreya-shankar", "type": "references", "note": "and colleagues — means grading outputs is how criteria get defined), and automating too much (LLMs can wire up plumbing but cannot look at t" }, { "source": "wiki:error-analysis-and-evals", "target": "wiki:automated-eval-engineering", "type": "references", "note": null }, { "source": "wiki:error-analysis-and-evals", "target": "wiki:closed-loop-agent-improvement", "type": "references", "note": null }, { "source": "wiki:error-analysis-and-evals", "target": "wiki:designing-for-verifiability", "type": "references", "note": null }, { "source": "wiki:error-analysis-and-evals", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:error-analysis-and-evals", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:eval-driven-development", "target": "wiki:airbnb", "type": "references", "note": "and formalised in methodology by hamel-husain and shreya-shankar, EDD treats evaluation as an ongoing development loop rather than a post-ho" }, { "source": "wiki:eval-driven-development", "target": "wiki:eval-taxonomy", "type": "references", "note": "the three-tier classification (deterministic, LLM-as-judge, human) underlying EDD." }, { "source": "wiki:eval-driven-development", "target": "wiki:agentic-code-quality", "type": "references", "note": "multi-tier control architecture" }, { "source": "wiki:eval-driven-development", "target": "wiki:generator-evaluator-loop", "type": "references", "note": "iterative refinement loop" }, { "source": "wiki:eval-driven-development", "target": "wiki:error-analysis-and-evals", "type": "references", "note": "diagnostic methodology" }, { "source": "wiki:eval-driven-development", "target": "wiki:hamel-husain", "type": "references", "note": "evaluation authority" }, { "source": "wiki:eval-driven-development", "target": "wiki:shreya-shankar", "type": "references", "note": "evaluator alignment research" }, { "source": "wiki:eval-taxonomy", "target": "wiki:structured-outputs", "type": "references", "note": "is the cheapest deterministic oracle." }, { "source": "wiki:eval-taxonomy", "target": "wiki:error-analysis-and-evals", "type": "references", "note": "and eval-driven-development for the broader discipline, evals-skills for evals as agent skills." }, { "source": "wiki:evals-skills", "target": "wiki:hamel-husain", "type": "references", "note": "and shreya-shankar, evals skills are \"a set of skills for AI product evals\" that encode lessons \"from helping 50+ companies and teaching stu" }, { "source": "wiki:evals-skills", "target": "wiki:subagents-and-context-management", "type": "references", "note": null }, { "source": "wiki:evals-skills", "target": "wiki:error-analysis-and-evals", "type": "references", "note": null }, { "source": "wiki:evals-skills", "target": "wiki:automated-eval-engineering", "type": "references", "note": null }, { "source": "wiki:evals-skills", "target": "wiki:designing-for-verifiability", "type": "references", "note": null }, { "source": "wiki:evals-skills", "target": "wiki:progressive-disclosure", "type": "references", "note": null }, { "source": "wiki:feynman-technique", "target": "wiki:richard-feynman", "type": "references", "note": "; his Caltech colleagues called him \"the great" }, { "source": "wiki:feynman-technique", "target": "wiki:build-from-scratch-pedagogy", "type": "references", "note": "for deep technical" }, { "source": "wiki:feynman-technique", "target": "wiki:first-principles-thinking", "type": "references", "note": ", build-from-scratch-pedagogy, richard-feynman, andrej-karpathy." }, { "source": "wiki:first-principles-thinking", "target": "wiki:richard-feynman", "type": "references", "note": "'s working mode —" }, { "source": "wiki:first-principles-thinking", "target": "wiki:build-from-scratch-pedagogy", "type": "references", "note": "is first principles as a learning tool;" }, { "source": "wiki:first-principles-thinking", "target": "wiki:karpathy-four-guidelines", "type": "references", "note": "#1 is first principles as coding conduct." }, { "source": "wiki:first-principles-thinking", "target": "wiki:grilling-doctrine", "type": "references", "note": "operationalizes it conversationally: facts checked, decisions human." }, { "source": "wiki:five-debts-of-agentic-engineering", "target": "wiki:grilling-doctrine", "type": "references", "note": "and formal specifications (to-spec). Interrogate the decision frontier, explicitly document non-goals, and establish observable acceptance c" }, { "source": "wiki:five-debts-of-agentic-engineering", "target": "wiki:smart-zone", "type": "references", "note": ") and inducing context-rot." }, { "source": "wiki:five-debts-of-agentic-engineering", "target": "wiki:context-engineering", "type": "references", "note": "via canonical CONTEXT.md (ubiquitous language), CONTEXT-MAP.md, and Architectural Decision Records (ADRs)." }, { "source": "wiki:five-debts-of-agentic-engineering", "target": "wiki:red-green-tdd", "type": "references", "note": "at public seams, agentic-manual-testing, and protected baseline regression suites that remain read-only to the agent." }, { "source": "wiki:five-debts-of-agentic-engineering", "target": "wiki:clean-architecture", "type": "references", "note": "boundaries, the deletion test (deep modules hiding substantial behavior behind small interfaces), and mandatory human walkthroughs." }, { "source": "wiki:five-debts-of-agentic-engineering", "target": "wiki:agent-containment-and-blast-radius", "type": "references", "note": ", least-privilege sandboxes, strict path allowlists, and immutable audit trails." }, { "source": "wiki:five-debts-of-agentic-engineering", "target": "wiki:software-engineering-fundamentals-for-agents", "type": "references", "note": "The foundational engineering competencies required to prevent these debts." }, { "source": "wiki:five-debts-of-agentic-engineering", "target": "wiki:agentic-code-quality", "type": "references", "note": "The risk-conditioned T0–T5 verification architecture." }, { "source": "wiki:five-debts-of-agentic-engineering", "target": "wiki:agent-harness-engineering", "type": "references", "note": "Designing runtime infrastructure around the model." }, { "source": "wiki:five-debts-of-agentic-engineering", "target": "wiki:releasable-patch-rate", "type": "references", "note": "Measuring quality across all five dimensions at the release boundary." }, { "source": "wiki:five-debts-of-agentic-engineering", "target": "wiki:constraint-layering", "type": "references", "note": "Allocating controls to the cheapest reliable layer." }, { "source": "wiki:generator-evaluator-loop", "target": "wiki:prithvi-rajasekaran", "type": "references", "note": "of anthropic's Labs team, that separates the agent doing the work from the agent judging it. Taking \"inspiration from Generative Adversarial" }, { "source": "wiki:generator-evaluator-loop", "target": "wiki:handoff-artifacts", "type": "references", "note": null }, { "source": "wiki:generator-evaluator-loop", "target": "wiki:context-rot", "type": "references", "note": "on long tasks. Compaction summarizes earlier conversation in place so the same agent continues on a shortened history; context resets clear " }, { "source": "wiki:generator-evaluator-loop", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:generator-evaluator-loop", "target": "wiki:multi-agent-orchestration", "type": "references", "note": null }, { "source": "wiki:generator-evaluator-loop", "target": "wiki:agentic-manual-testing", "type": "references", "note": null }, { "source": "wiki:generator-evaluator-loop", "target": "wiki:error-analysis-and-evals", "type": "references", "note": null }, { "source": "wiki:git-for-agentic-workflows", "target": "wiki:simon-willison", "type": "references", "note": null }, { "source": "wiki:git-for-agentic-workflows", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:git-for-agentic-workflows", "target": "wiki:idea-to-ship-flow", "type": "references", "note": null }, { "source": "wiki:git-for-agentic-workflows", "target": "wiki:karpathy-four-guidelines", "type": "references", "note": null }, { "source": "wiki:grill-with-docs", "target": "wiki:matt-pocock", "type": "references", "note": "on the grilling-doctrine primitive, it conducts a conversational interview to establish shared human-agent understanding while progressively" }, { "source": "wiki:grilling-doctrine", "target": "wiki:matt-pocock", "type": "references", "note": "'s interview primitive applied to human-agent collaboration. Core rule:" }, { "source": "wiki:grilling-doctrine", "target": "wiki:tracer-bullets", "type": "references", "note": null }, { "source": "wiki:grilling-doctrine", "target": "wiki:idea-to-ship-flow", "type": "references", "note": "and grill-with-docs for the full pipeline." }, { "source": "wiki:grilling-doctrine", "target": "wiki:richard-feynman", "type": "references", "note": ", feynman-technique, context-engineering, idea-to-ship-flow, grill-with-docs." }, { "source": "wiki:handoff-artifacts", "target": "wiki:smart-zone", "type": "references", "note": ", context-rot, idea-to-ship-flow, progressive-disclosure, ai-coding-taxonomy." }, { "source": "wiki:hexagonal-architecture", "target": "wiki:alistair-cockburn", "type": "references", "note": "that isolates business logic from external systems through well-defined interfaces. This pattern directly influenced clean-architecture and " }, { "source": "wiki:hexagonal-architecture", "target": "wiki:robert-c-martin", "type": "references", "note": "'s clean-architecture synthesis incorporated hexagonal architecture principles, particularly:" }, { "source": "wiki:hexagonal-architecture", "target": "wiki:dependency-rule", "type": "references", "note": "compliance — dependencies point toward business logic" }, { "source": "wiki:hexagonal-architecture", "target": "wiki:steve-freeman", "type": "references", "note": "and nat-pryce in \"Growing Object Oriented Software\" and became a foundational element in the broader architectural synthesis that led to cle" }, { "source": "wiki:hoard-and-recombine", "target": "wiki:simon-willison", "type": "references", "note": null }, { "source": "wiki:hoard-and-recombine", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:hoard-and-recombine", "target": "wiki:build-from-scratch-pedagogy", "type": "references", "note": null }, { "source": "wiki:hoard-and-recombine", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:hoard-and-recombine", "target": "wiki:tracer-bullets", "type": "references", "note": null }, { "source": "wiki:idea-to-ship-flow", "target": "wiki:matt-pocock", "type": "references", "note": "'s structured engineering system, distilled. The pipeline from fuzzy idea to shipped" }, { "source": "wiki:idea-to-ship-flow", "target": "wiki:grilling-doctrine", "type": "references", "note": null }, { "source": "wiki:idea-to-ship-flow", "target": "wiki:tracer-bullets", "type": "references", "note": null }, { "source": "wiki:idea-to-ship-flow", "target": "wiki:tdd-with-agents", "type": "references", "note": null }, { "source": "wiki:karpathy-four-guidelines", "target": "wiki:andrej-karpathy", "type": "references", "note": "'s pitfall" }, { "source": "wiki:karpathy-four-guidelines", "target": "wiki:tdd-with-agents", "type": "references", "note": "in miniature and powers tracer-bullets. #1 is" }, { "source": "wiki:karpathy-four-guidelines", "target": "wiki:grilling-doctrine", "type": "references", "note": "at code scale. #2-3 are what keeps codebases maintainable for agents." }, { "source": "wiki:llm-app-improvement-ladder", "target": "wiki:structured-outputs", "type": "references", "note": null }, { "source": "wiki:llm-app-improvement-ladder", "target": "wiki:think-tool", "type": "references", "note": null }, { "source": "wiki:llm-app-improvement-ladder", "target": "wiki:tool-calling-loop", "type": "references", "note": null }, { "source": "wiki:llm-app-improvement-ladder", "target": "wiki:agents-vs-workflows", "type": "references", "note": null }, { "source": "wiki:llm-app-improvement-ladder", "target": "wiki:generator-evaluator-loop", "type": "references", "note": null }, { "source": "wiki:llm-app-improvement-ladder", "target": "wiki:eval-taxonomy", "type": "references", "note": "at every step, or you're climbing blind." }, { "source": "wiki:llm-message-protocol", "target": "wiki:context-rot", "type": "references", "note": "compound with history length." }, { "source": "wiki:llm-message-protocol", "target": "wiki:tool-calling-loop", "type": "references", "note": null }, { "source": "wiki:llm-message-protocol", "target": "wiki:context-engineering", "type": "references", "note": ", handoff-artifacts)." }, { "source": "wiki:llm-message-protocol", "target": "wiki:llm-app-improvement-ladder", "type": "references", "note": "the ordered improvement techniques built on this protocol." }, { "source": "wiki:llm-wiki-pattern", "target": "wiki:andrej-karpathy", "type": "references", "note": "'s approach to durable knowledge: compile it once into interlinked" }, { "source": "wiki:llm-wiki-pattern", "target": "wiki:context-engineering", "type": "references", "note": "(Matt) is the same idea applied to project instructions" }, { "source": "wiki:llm-wiki-pattern", "target": "wiki:agent-native-infrastructure", "type": "references", "note": null }, { "source": "wiki:model-context-protocol-basics", "target": "wiki:tool-calling-loop", "type": "references", "note": "describes the in-conversation mechanics (tool calls and results inside the message history), MCP describes the plumbing: a client-server pro" }, { "source": "wiki:model-context-protocol-basics", "target": "wiki:context-budget-audit", "type": "references", "note": "cost, not free observability." }, { "source": "wiki:model-context-protocol-basics", "target": "wiki:agent-harness-engineering", "type": "references", "note": ") can grow its capability surface by plugging in MCP servers without changing its core loop — the same model-provider-abstraction logic appl" }, { "source": "wiki:model-provider-abstraction", "target": "wiki:vercel", "type": "references", "note": ", is the reference implementation) that any ask(prompt, model) function accepts — and route all generation through it:" }, { "source": "wiki:model-provider-abstraction", "target": "wiki:dependency-inversion-principle", "type": "references", "note": "applied to LLM infrastructure: the application depends on an abstraction it owns, not on a vendor SDK. It also de-risks context-rot economic" }, { "source": "wiki:model-provider-abstraction", "target": "wiki:llm-message-protocol", "type": "references", "note": ", structured-outputs, dependency-inversion-principle, clean-architecture, agent-native-infrastructure." }, { "source": "wiki:multi-agent-orchestration", "target": "wiki:context-rot", "type": "references", "note": null }, { "source": "wiki:multi-agent-orchestration", "target": "wiki:subagents-and-context-management", "type": "references", "note": "for specific exploratory or implementation subtasks. Each subagent operates in its own fresh context, runs tools in parallel, and returns on" }, { "source": "wiki:multi-agent-orchestration", "target": "wiki:agents-vs-workflows", "type": "references", "note": null }, { "source": "wiki:multi-agent-orchestration", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:multi-agent-orchestration", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:multi-agent-orchestration", "target": "wiki:automated-eval-engineering", "type": "references", "note": null }, { "source": "wiki:multi-agent-orchestration", "target": "wiki:conformance-suites-as-fitness-functions", "type": "references", "note": null }, { "source": "wiki:onion-architecture", "target": "wiki:jeffrey-palermo", "type": "references", "note": "that organizes software into concentric layers with dependencies pointing inward toward the core domain. This pattern directly influenced cl" }, { "source": "wiki:onion-architecture", "target": "wiki:robert-c-martin", "type": "references", "note": "'s clean-architecture synthesis adopted the onion pattern's:" }, { "source": "wiki:onion-architecture", "target": "wiki:dependency-rule", "type": "references", "note": null }, { "source": "wiki:progressive-disclosure", "target": "wiki:context-rot", "type": "references", "note": "and prompt-bloat." }, { "source": "wiki:progressive-disclosure", "target": "wiki:editorial-diagrams-and-visual-explanations", "type": "references", "note": "by routing high-level structural overviews first before loading deep implementation schemas." }, { "source": "wiki:progressive-disclosure", "target": "wiki:prompt-bloat", "type": "references", "note": ", context-engineering, agents-md-spec, smart-zone." }, { "source": "wiki:prompt-bloat", "target": "wiki:context-rot", "type": "references", "note": ", progressive-disclosure, agents-md-spec, context-engineering." }, { "source": "wiki:red-green-tdd", "target": "wiki:eval-driven-development", "type": "references", "note": "and tdd-with-agents." }, { "source": "wiki:red-green-tdd", "target": "wiki:conformance-suites-as-fitness-functions", "type": "references", "note": null }, { "source": "wiki:red-green-tdd", "target": "wiki:simon-willison", "type": "references", "note": "source of the agentic-engineering pattern" }, { "source": "wiki:red-green-tdd", "target": "wiki:tdd-with-agents", "type": "references", "note": "broader agent TDD workflow" }, { "source": "wiki:red-green-tdd", "target": "wiki:agentic-manual-testing", "type": "references", "note": ", karpathy-four-guidelines, agentic-engineering-patterns" }, { "source": "wiki:releasable-patch-rate", "target": "wiki:agentic-code-quality", "type": "references", "note": "The risk-conditioned control architecture." }, { "source": "wiki:releasable-patch-rate", "target": "wiki:agentic-software-factory", "type": "references", "note": "Operating models for autonomous development at scale." }, { "source": "wiki:releasable-patch-rate", "target": "wiki:five-debts-of-agentic-engineering", "type": "references", "note": "Debt categories that reduce patch releasability." }, { "source": "wiki:releasable-patch-rate", "target": "wiki:conformance-suites-as-fitness-functions", "type": "references", "note": "Deterministic fitness functions for autonomous loops." }, { "source": "wiki:site-as-eval-subject-grading", "target": "wiki:eval-driven-development", "type": "references", "note": "from prompts to shipped" }, { "source": "wiki:site-as-eval-subject-grading", "target": "wiki:conformance-suites-as-fitness-functions", "type": "references", "note": ": ambiguous" }, { "source": "wiki:site-as-eval-subject-grading", "target": "wiki:agentic-code-quality", "type": "references", "note": null }, { "source": "wiki:site-as-eval-subject-grading", "target": "wiki:designing-for-verifiability", "type": "references", "note": "applies to the" }, { "source": "wiki:site-as-eval-subject-grading", "target": "wiki:eval-taxonomy", "type": "references", "note": "(three tiers), conformance-suites-as-fitness-functions" }, { "source": "wiki:site-as-eval-subject-grading", "target": "wiki:generator-evaluator-loop", "type": "references", "note": null }, { "source": "wiki:skill-treatment-effect", "target": "wiki:evals-skills", "type": "references", "note": ", SKILL.md) into an agent's context during inference. Empirical benchmarks demonstrate that skills are not a universal productivity booster;" }, { "source": "wiki:skill-treatment-effect", "target": "wiki:prompt-bloat", "type": "references", "note": "and increases inference latency without moving verification needles." }, { "source": "wiki:skill-treatment-effect", "target": "wiki:agent-harness-engineering", "type": "references", "note": "Harness architecture and runtime orchestration." }, { "source": "wiki:skill-treatment-effect", "target": "wiki:progressive-disclosure", "type": "references", "note": "Staged context loading to avoid token saturation." }, { "source": "wiki:smart-zone", "target": "wiki:handoff-artifacts", "type": "references", "note": "and start a fresh session context." }, { "source": "wiki:smart-zone", "target": "wiki:context-rot", "type": "references", "note": ", handoff-artifacts, context-engineering, subagents-and-context-management, ai-coding-taxonomy." }, { "source": "wiki:software-engineering-fundamentals-for-agents", "target": "wiki:andrew-ng", "type": "references", "note": ". It posits that while coding agents make syntax generation virtually free, deep comprehension of core software fundamentals is the decisive" }, { "source": "wiki:software-engineering-fundamentals-for-agents", "target": "wiki:ai-engineer-role", "type": "references", "note": "the role definition that motivates these fundamentals. Concepts" }, { "source": "wiki:software-engineering-fundamentals-for-agents", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": "Disciplined verification loops (Simon Willison)." }, { "source": "wiki:software-engineering-fundamentals-for-agents", "target": "wiki:five-debts-of-agentic-engineering", "type": "references", "note": "The structural failure modes of unguided agentic code." }, { "source": "wiki:software-engineering-fundamentals-for-agents", "target": "wiki:agent-containment-and-blast-radius", "type": "references", "note": "Restricting agent execution scope and operational risk." }, { "source": "wiki:software-engineering-fundamentals-for-agents", "target": "wiki:clean-architecture", "type": "references", "note": "Maintaining strict modular boundaries across evolving systems." }, { "source": "wiki:software-engineering-fundamentals-for-agents", "target": "wiki:context-engineering", "type": "references", "note": "Structuring the information environment provided to AI models." }, { "source": "wiki:structured-outputs", "target": "wiki:tool-calling-loop", "type": "references", "note": "infrastructure — declare a tool whose arguments are your schema and force the model to call it — to get the same shape guarantees without a " }, { "source": "wiki:structured-outputs", "target": "wiki:evals-skills", "type": "references", "note": "schema conformance is cheap to verify automatically, a rare machine-checkable oracle." }, { "source": "wiki:structured-outputs", "target": "wiki:llm-message-protocol", "type": "references", "note": ", tool-calling-loop, model-provider-abstraction, evals-skills, generator-evaluator-loop." }, { "source": "wiki:subagents-and-context-management", "target": "wiki:simon-willison", "type": "references", "note": null }, { "source": "wiki:subagents-and-context-management", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:subagents-and-context-management", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:subagents-and-context-management", "target": "wiki:karpathy-four-guidelines", "type": "references", "note": null }, { "source": "wiki:tdd-with-agents", "target": "wiki:matt-pocock", "type": "references", "note": ": \"Bad code is now the most expensive it has ever been.\" Agents ship volume." }, { "source": "wiki:tdd-with-agents", "target": "wiki:karpathy-four-guidelines", "type": "references", "note": null }, { "source": "wiki:tdd-with-agents", "target": "wiki:red-green-tdd", "type": "references", "note": "and simon-willison's agentic-engineering-patterns." }, { "source": "wiki:tdd-with-agents", "target": "wiki:tracer-bullets", "type": "references", "note": "ticket should ship with its test — the slice is" }, { "source": "wiki:think-tool", "target": "wiki:tool-calling-loop", "type": "references", "note": "can make better decisions.^[raw/aihero/implementing-anthropics-think-tool-in-typescript.md]" }, { "source": "wiki:think-tool", "target": "wiki:llm-message-protocol", "type": "references", "note": "history does the rest. Echoes ReAct and Reflexion." }, { "source": "wiki:think-tool", "target": "wiki:smart-zone", "type": "references", "note": "and context staging: put the right information in the right place in history for the decision that needs it." }, { "source": "wiki:tool-calling-loop", "target": "wiki:context-rot", "type": "references", "note": ", lost-in-the-middle). Many frameworks recommend staying under ~6 tools; issues can appear as low as 12. Tool-count discipline is therefore " }, { "source": "wiki:tool-calling-loop", "target": "wiki:llm-message-protocol", "type": "references", "note": ", model-context-protocol-basics, context-rot, agent-harness-engineering, generator-evaluator-loop." }, { "source": "wiki:tracer-bullets", "target": "wiki:matt-pocock", "type": "references", "note": "repurposes it as the main defense" }, { "source": "wiki:tracer-bullets", "target": "wiki:richard-feynman", "type": "references", "note": ": \"nature cannot be fooled\" — production either)." }, { "source": "wiki:tracer-bullets", "target": "wiki:karpathy-four-guidelines", "type": "references", "note": null }, { "source": "wiki:tracer-bullets", "target": "wiki:tdd-with-agents", "type": "references", "note": ". See idea-to-ship-flow." }, { "source": "wiki:tracer-bullets", "target": "wiki:idea-to-ship-flow", "type": "references", "note": ", tdd-with-agents, karpathy-four-guidelines, richard-feynman." }, { "source": "wiki:addy-osmani", "target": "wiki:agentic-code-quality", "type": "references", "note": "constraint-driven verification and multi-tier feedback" }, { "source": "wiki:addy-osmani", "target": "wiki:agent-harness-engineering", "type": "references", "note": "operating systems and harnesses for autonomous agents" }, { "source": "wiki:addy-osmani", "target": "wiki:agentic-software-factory", "type": "references", "note": "operating model for scaled agent delivery" }, { "source": "wiki:addy-osmani", "target": "wiki:simon-willison", "type": "references", "note": "contemporary in developer tooling and AI workflows" }, { "source": "wiki:addy-osmani", "target": "wiki:viv-trivedy", "type": "references", "note": "harness engineering pioneer" }, { "source": "wiki:aditi-raghunathan", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:aditi-raghunathan", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:ahmed-e-hassan", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:ahmed-e-hassan", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:airbnb", "target": "wiki:eval-driven-development", "type": "references", "note": "(EDD) for GenAI systems at scale.^[raw/articles/airbnb-eval-driven-development-2026.md]" }, { "source": "wiki:airbnb", "target": "wiki:agentic-code-quality", "type": "references", "note": "multi-tier quality architecture" }, { "source": "wiki:airbnb", "target": "wiki:error-analysis-and-evals", "type": "references", "note": "trace analysis" }, { "source": "wiki:airbnb", "target": "wiki:hamel-husain", "type": "references", "note": "evals methodology" }, { "source": "wiki:alistair-cockburn", "target": "wiki:hexagonal-architecture", "type": "references", "note": "(also known as Ports and Adapters pattern). His architectural pattern influenced clean-architecture and emphasizes isolating business logic " }, { "source": "wiki:alistair-cockburn", "target": "wiki:steve-freeman", "type": "references", "note": "and nat-pryce in their book \"Growing Object Oriented Software\" and integrated into robert-c-martin's clean-architecture synthesis." }, { "source": "wiki:alistair-cockburn", "target": "wiki:clean-architecture", "type": "references", "note": "incorporates his hexagonal patterns" }, { "source": "wiki:andrei-botocan", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:andrei-botocan", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:andrej-karpathy", "target": "wiki:karpathy-four-guidelines", "type": "references", "note": ": think before coding, simplicity first, surgical changes," }, { "source": "wiki:andrej-karpathy", "target": "wiki:build-from-scratch-pedagogy", "type": "references", "note": ": micrograd before PyTorch, nanoGPT before the library." }, { "source": "wiki:andrej-karpathy", "target": "wiki:llm-wiki-pattern", "type": "references", "note": ": compile knowledge once into interlinked markdown, keep it current," }, { "source": "wiki:andrej-karpathy", "target": "wiki:conformance-suites-as-fitness-functions", "type": "references", "note": null }, { "source": "wiki:andrej-karpathy", "target": "wiki:richard-feynman", "type": "references", "note": "disciple in method. His guidelines operationalize" }, { "source": "wiki:andrej-karpathy", "target": "wiki:matt-pocock", "type": "references", "note": "'s \"make codebases agents love\" at the single-change level (per aihero.dev: \"design" }, { "source": "wiki:andrew-ng", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": "Disciplined practices distinguishing engineering from vibe coding." }, { "source": "wiki:andrew-ng", "target": "wiki:software-engineering-fundamentals-for-agents", "type": "references", "note": "The 5-pillar taxonomy for steering coding agents." }, { "source": "wiki:andrew-ng", "target": "wiki:five-debts-of-agentic-engineering", "type": "references", "note": "The structural failure modes of unsteered probabilistic code generation." }, { "source": "wiki:andrew-ng", "target": "wiki:andrej-karpathy", "type": "references", "note": "Co-educator in AI pedagogy and advocate of foundational comprehension." }, { "source": "wiki:anil-madhavapeddy", "target": "wiki:agentic-vulnerability-lifecycle", "type": "references", "note": "the disclosure-window failure his report illustrates" }, { "source": "wiki:anil-madhavapeddy", "target": "wiki:agent-containment-and-blast-radius", "type": "references", "note": "mitigation strategies for agent-accelerated security threats" }, { "source": "wiki:anthropic", "target": "wiki:multi-agent-orchestration", "type": "references", "note": ".^[raw/articles/anthropic-multi-agent-research-system-2025.md]" }, { "source": "wiki:anthropic", "target": "wiki:agent-containment-and-blast-radius", "type": "references", "note": ".^[raw/articles/anthropic-engineering-how-we-contain-claude-2026.md]" }, { "source": "wiki:anthropic", "target": "wiki:claude-managed-agents", "type": "references", "note": ", a hosted infrastructure suite decoupling agent reasoning loops from containerized sandbox execution, exposing stateful event streams for t" }, { "source": "wiki:anthropic", "target": "wiki:copilotkit", "type": "references", "note": "AG-UI integration partner" }, { "source": "wiki:anthropic", "target": "wiki:simon-willison", "type": "references", "note": "LLM and AI tooling space" }, { "source": "wiki:anthropic", "target": "wiki:shreya-shankar", "type": "references", "note": "AI/ML research community" }, { "source": "wiki:anthropic", "target": "wiki:jarred-sumner", "type": "references", "note": "Claude model usage" }, { "source": "wiki:armin-ronacher", "target": "wiki:mario-zechner", "type": "references", "note": "shared development velocity concerns" }, { "source": "wiki:armin-ronacher", "target": "wiki:james-shore", "type": "references", "note": "maintenance and economic concerns" }, { "source": "wiki:armin-ronacher", "target": "wiki:simon-willison", "type": "references", "note": "contemporary in developer community" }, { "source": "wiki:beatrice-casey", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:beatrice-casey", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:beth-barnes", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:beth-barnes", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:boris-cherny", "target": "wiki:anthropic", "type": "references", "note": "organization" }, { "source": "wiki:boris-cherny", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": "verification patterns" }, { "source": "wiki:boris-cherny", "target": "wiki:agent-harness-engineering", "type": "references", "note": "harness architecture" }, { "source": "wiki:boris-cherny", "target": "wiki:gergely-orosz", "type": "references", "note": "Pragmatic Engineer deep dive" }, { "source": "wiki:brittany-reid", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:brittany-reid", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:cathryn-lavery", "target": "wiki:editorial-diagrams-and-visual-explanations", "type": "references", "note": null }, { "source": "wiki:cathryn-lavery", "target": "wiki:cognitive-debt-and-walkthroughs", "type": "references", "note": "at the visual communication layer. Where richard-feynman emphasizes plain-spoken pedagogy, andrej-karpathy enforces code simplicity, and sim" }, { "source": "wiki:cathryn-lavery", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:cathryn-lavery", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:cathryn-lavery", "target": "wiki:progressive-disclosure", "type": "references", "note": null }, { "source": "wiki:christoph-csallner", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:christoph-csallner", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:christoph-nakazawa", "target": "wiki:constraint-layering", "type": "references", "note": "and supply the Tier 1 backpressure described in agentic-code-quality." }, { "source": "wiki:christoph-nakazawa", "target": "wiki:deterministic-lint-gates", "type": "references", "note": "the pattern his config exemplifies" }, { "source": "wiki:christoph-nakazawa", "target": "wiki:agentic-code-quality", "type": "references", "note": "multi-tier verification architecture" }, { "source": "wiki:copilotkit", "target": "wiki:ag-ui-protocol", "type": "references", "note": ".^[raw/articles/ag-ui-protocol-specification-2026.md]" }, { "source": "wiki:copilotkit", "target": "wiki:anthropic", "type": "references", "note": "to release first-class AG-UI adapters for claude-managed-agents, standardizing Anthropic's hosted event logs into client-rendered generative" }, { "source": "wiki:copilotkit", "target": "wiki:claude-managed-agents", "type": "references", "note": "hosted agent platform integration" }, { "source": "wiki:copilotkit", "target": "wiki:agent-native-infrastructure", "type": "references", "note": "execution tier" }, { "source": "wiki:cursor", "target": "wiki:wilson-lin", "type": "references", "note": "Cursor team researcher" }, { "source": "wiki:cursor", "target": "wiki:simon-willison", "type": "references", "note": "developer tooling space" }, { "source": "wiki:cursor", "target": "wiki:anthropic", "type": "references", "note": "Claude model usage" }, { "source": "wiki:david-gros", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:david-gros", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:david-rein", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:david-rein", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:deepseek", "target": "wiki:cordis-framework", "type": "references", "note": "as an in-process microkernel where every agent subsystem (models, tools, skills, sessions, sandboxes, storage, loops, scheduling, and UI) is" }, { "source": "wiki:deepseek", "target": "wiki:deepseek-harness", "type": "references", "note": null }, { "source": "wiki:deepseek", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:deepseek", "target": "wiki:agent-native-infrastructure", "type": "references", "note": null }, { "source": "wiki:deepseek", "target": "wiki:anthropic", "type": "references", "note": null }, { "source": "wiki:dipayan-banik", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:dipayan-banik", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:dora", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "organizational evidence" }, { "source": "wiki:dora", "target": "wiki:agentic-software-factory", "type": "references", "note": "delivery operating model" }, { "source": "wiki:dora", "target": "wiki:agentic-code-quality", "type": "references", "note": "quality controls" }, { "source": "wiki:drew-breunig", "target": "wiki:simon-willison", "type": "references", "note": "quoted his post Fable & The End of the Free Lunch on 23rd August 2026.^[raw/articles/simon-willison-quoting-drew-breunig-2026.md]" }, { "source": "wiki:drew-breunig", "target": "wiki:context-engineering", "type": "references", "note": ", and agent-harness-engineering become durable work rather than throwaway glue." }, { "source": "wiki:drew-breunig", "target": "wiki:anthropic", "type": "references", "note": null }, { "source": "wiki:drew-breunig", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:dung-nguyen-manh", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:dung-nguyen-manh", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:eirini-kalliamvakou", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:eirini-kalliamvakou", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:epoch-ai", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "benchmark-validity evidence" }, { "source": "wiki:epoch-ai", "target": "wiki:error-analysis-and-evals", "type": "references", "note": "evaluation design" }, { "source": "wiki:epoch-ai", "target": "wiki:agentic-code-quality", "type": "references", "note": "oracle-health controls" }, { "source": "wiki:florian-brand", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:florian-brand", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:gelei-deng", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:gelei-deng", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:gergely-orosz", "target": "wiki:kent-beck", "type": "references", "note": "on TDD-governed agent workflows and boris-cherny on Claude Code's architectural harness and verification principles.^[raw/articles/kent-beck" }, { "source": "wiki:gergely-orosz", "target": "wiki:boris-cherny", "type": "references", "note": "Claude Code harness design" }, { "source": "wiki:gergely-orosz", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": "industry patterns" }, { "source": "wiki:gergely-orosz", "target": "wiki:agentic-code-quality", "type": "references", "note": "verification controls" }, { "source": "wiki:github", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": "disciplined agent workflows" }, { "source": "wiki:github", "target": "wiki:agentic-code-quality", "type": "references", "note": "specification and verification controls" }, { "source": "wiki:github", "target": "wiki:openai", "type": "references", "note": "Copilot partner" }, { "source": "wiki:hajimu-iida", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:hajimu-iida", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:hamel-husain", "target": "wiki:error-analysis-and-evals", "type": "references", "note": "on real production traces. Generic off-the-shelf metrics (like generic hallucination or helpfulness scores) create an illusion of progress w" }, { "source": "wiki:hamel-husain", "target": "wiki:shreya-shankar", "type": "references", "note": "on active-learning-assisted trace labeling and failure discovery tools." }, { "source": "wiki:hamel-husain", "target": "wiki:designing-for-verifiability", "type": "references", "note": ").^[raw/articles/hamel-husain-it-s-hard-to-eval-is-a-product-smell-2026.md]" }, { "source": "wiki:hamel-husain", "target": "wiki:automated-eval-engineering", "type": "references", "note": null }, { "source": "wiki:hamel-husain", "target": "wiki:closed-loop-agent-improvement", "type": "references", "note": null }, { "source": "wiki:hamel-husain", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:hao-li", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:hao-li", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:haoxiang-zhang", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:haoxiang-zhang", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:hiroshi-iwata", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:hiroshi-iwata", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:huy-nhat-phan", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:huy-nhat-phan", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:ivan-bercovich", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:ivan-bercovich", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:ivar-jacobson", "target": "wiki:clean-architecture", "type": "references", "note": "by establishing the separation between boundary interfaces, control logic, and core entities." }, { "source": "wiki:ivgeni-segal", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:ivgeni-segal", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:james-coplien", "target": "wiki:trygve-reenskaug", "type": "references", "note": "of DCI (Data, Context, and Interaction) architecture. His DCI pattern influenced robert-c-martin's clean-architecture synthesis by contribut" }, { "source": "wiki:james-coplien", "target": "wiki:clean-architecture", "type": "references", "note": "incorporates ideas from his DCI work" }, { "source": "wiki:james-shore", "target": "wiki:mario-zechner", "type": "references", "note": "shared concerns about development velocity" }, { "source": "wiki:james-shore", "target": "wiki:armin-ronacher", "type": "references", "note": "architectural complexity concerns" }, { "source": "wiki:james-shore", "target": "wiki:simon-willison", "type": "references", "note": "contemporary in developer community" }, { "source": "wiki:jarred-sumner", "target": "wiki:conformance-suites-as-fitness-functions", "type": "references", "note": null }, { "source": "wiki:jarred-sumner", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:jarred-sumner", "target": "wiki:tobias-lutke", "type": "references", "note": "autonomous optimization projects" }, { "source": "wiki:jarred-sumner", "target": "wiki:anthropic", "type": "references", "note": "Claude model usage" }, { "source": "wiki:jean-stanislas-denain", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:jean-stanislas-denain", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:jeffrey-palermo", "target": "wiki:onion-architecture", "type": "references", "note": ", a layered architectural pattern that influenced clean-architecture. His onion pattern emphasizes dependency inversion and separation of co" }, { "source": "wiki:jeffrey-palermo", "target": "wiki:robert-c-martin", "type": "references", "note": "'s clean-architecture synthesis and its emphasis on the dependency-rule." }, { "source": "wiki:jeffrey-palermo", "target": "wiki:clean-architecture", "type": "references", "note": "incorporates his onion layering approach" }, { "source": "wiki:joanna-c-s-santos", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:joanna-c-s-santos", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:joel-becker", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:joel-becker", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:johann-rehberger", "target": "wiki:armin-ronacher", "type": "references", "note": "system architecture concerns" }, { "source": "wiki:johann-rehberger", "target": "wiki:simon-willison", "type": "references", "note": "AI/security intersection" }, { "source": "wiki:johann-rehberger", "target": "wiki:shreya-shankar", "type": "references", "note": "AI safety community" }, { "source": "wiki:k-m-ferdous", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:k-m-ferdous", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:kenichi-yamaguchi", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:kenichi-yamaguchi", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:kent-beck", "target": "wiki:gergely-orosz", "type": "references", "note": ", Beck characterized AI coding agents as an \"unpredictable genie\" that fulfills requests literally but often through unexpected or unprincip" }, { "source": "wiki:kent-beck", "target": "wiki:agentic-code-quality", "type": "references", "note": null }, { "source": "wiki:kent-beck", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": "TDD governor and patterns" }, { "source": "wiki:kent-beck", "target": "wiki:red-green-tdd", "type": "references", "note": "test-driven cycles" }, { "source": "wiki:kent-beck", "target": "wiki:martin-fowler", "type": "references", "note": "collaborator on agile and software design" }, { "source": "wiki:kexun-zhang", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:kexun-zhang", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:kowshik-chowdhury", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:kowshik-chowdhury", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:lalit-maganti", "target": "wiki:conformance-suites-as-fitness-functions", "type": "references", "note": "with the limits described by cognitive-debt-and-walkthroughs. It is a concrete example of why agentic-engineering-patterns need explicit hum" }, { "source": "wiki:lalit-maganti", "target": "wiki:cognitive-debt-and-walkthroughs", "type": "references", "note": null }, { "source": "wiki:lalit-maganti", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:lalit-maganti", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:leo-yu-zhang", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:leo-yu-zhang", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:maliheh-izadi", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:maliheh-izadi", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:mario-zechner", "target": "wiki:armin-ronacher", "type": "references", "note": "architectural complexity concerns" }, { "source": "wiki:mario-zechner", "target": "wiki:james-shore", "type": "references", "note": "maintenance cost economics" }, { "source": "wiki:mario-zechner", "target": "wiki:simon-willison", "type": "references", "note": "contemporary in developer community" }, { "source": "wiki:martin-fowler", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": "comprehension loops and TDD" }, { "source": "wiki:martin-fowler", "target": "wiki:kent-beck", "type": "references", "note": "longtime collaborator on XP and agile" }, { "source": "wiki:martin-fowler", "target": "wiki:cognitive-debt-and-walkthroughs", "type": "references", "note": "human comprehension in AI systems" }, { "source": "wiki:martin-fowler", "target": "wiki:agentic-code-quality", "type": "references", "note": "quality control architecture" }, { "source": "wiki:matt-pocock", "target": "wiki:llm-message-protocol", "type": "references", "note": "(stateless message histories, system prompts, token economics), the tool-calling-loop (with the under-6-tools rule of thumb), structured-out" }, { "source": "wiki:matt-pocock", "target": "wiki:grilling-doctrine", "type": "references", "note": "and grill-with-docs)." }, { "source": "wiki:matt-pocock", "target": "wiki:tracer-bullets", "type": "references", "note": null }, { "source": "wiki:matt-pocock", "target": "wiki:progressive-disclosure", "type": "references", "note": null }, { "source": "wiki:matt-pocock", "target": "wiki:richard-feynman", "type": "references", "note": ", andrej-karpathy, idea-to-ship-flow, grilling-doctrine, tracer-bullets, context-engineering, ai-coding-taxonomy." }, { "source": "wiki:mert-demirer", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:mert-demirer", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:miku-watanabe", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:miku-watanabe", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:minh-vu-thai-pham", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:minh-vu-thai-pham", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:model-evaluation-and-threat-research", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "benchmark and productivity evidence" }, { "source": "wiki:model-evaluation-and-threat-research", "target": "wiki:error-analysis-and-evals", "type": "references", "note": "evaluation design and error analysis" }, { "source": "wiki:model-evaluation-and-threat-research", "target": "wiki:agentic-code-quality", "type": "references", "note": "proposed factory controls" }, { "source": "wiki:mohammed-latif-siddiq", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:mohammed-latif-siddiq", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:nat-pryce", "target": "wiki:steve-freeman", "type": "references", "note": "of \"Growing Object Oriented Software\" who adopted alistair-cockburn's hexagonal-architecture pattern. Their book helped establish the Ports " }, { "source": "wiki:nat-pryce", "target": "wiki:hexagonal-architecture", "type": "references", "note": "adopted and promoted Cockburn's pattern with Freeman" }, { "source": "wiki:nat-pryce", "target": "wiki:clean-architecture", "type": "references", "note": "contributed to the architectural foundations" }, { "source": "wiki:nate-rush", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:nate-rush", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:nghi-d-q-bui", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:nghi-d-q-bui", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:nick-craig-wood", "target": "wiki:agentic-vulnerability-lifecycle", "type": "references", "note": "the disclosure volume surge phenomenon" }, { "source": "wiki:nick-craig-wood", "target": "wiki:agent-containment-and-blast-radius", "type": "references", "note": "strategies for managing high-volume agent-generated security reports" }, { "source": "wiki:openai", "target": "wiki:codex-harness-architecture", "type": "references", "note": "coding harness and the Agents SDK." }, { "source": "wiki:openai", "target": "wiki:agent-harness-engineering", "type": "references", "note": "runtime infrastructure, sandboxes, and tool contracts" }, { "source": "wiki:openai", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "benchmark validity and code-quality evidence" }, { "source": "wiki:openai", "target": "wiki:anthropic", "type": "references", "note": "peer AI frontier research lab" }, { "source": "wiki:openai", "target": "wiki:deepseek", "type": "references", "note": "developer of open-weights models and modular harness runtimes" }, { "source": "wiki:openai", "target": "wiki:simon-willison", "type": "references", "note": "analysis of coding agent loops and harness patterns" }, { "source": "wiki:peter-cihon", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:peter-cihon", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:prem-devanbu", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:prem-devanbu", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:prithvi-rajasekaran", "target": "wiki:anthropic", "type": "references", "note": "'s Labs team and author of Harness design for long-running application development (Mar 24, 2026). Worked on \"two interconnected problems: g" }, { "source": "wiki:prithvi-rajasekaran", "target": "wiki:generator-evaluator-loop", "type": "references", "note": ": a generator/evaluator pair for frontend design, extended to a three-agent planner–generator–evaluator harness for multi-hour autonomous fu" }, { "source": "wiki:prithvi-rajasekaran", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:rahul-pandita", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:rahul-pandita", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:razvan-mihai-popescu", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:razvan-mihai-popescu", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:richard-feynman", "target": "wiki:build-from-scratch-pedagogy", "type": "references", "note": null }, { "source": "wiki:richard-feynman", "target": "wiki:first-principles-thinking", "type": "references", "note": ", feynman-technique, build-from-scratch-pedagogy, andrej-karpathy, simon-willison." }, { "source": "wiki:robert-c-martin", "target": "wiki:clean-architecture", "type": "references", "note": "approach, establishing the dependency-rule as the core organizing principle. His architectural model integrates ideas from hexagonal-archite" }, { "source": "wiki:robert-c-martin", "target": "wiki:dependency-rule", "type": "references", "note": "the core principle governing clean architecture boundaries" }, { "source": "wiki:sabrina-haque", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:sabrina-haque", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:sarvesh-ingale", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:sarvesh-ingale", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:shashwat-saxena", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:shashwat-saxena", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:shazibul-islam-shamim", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:shazibul-islam-shamim", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:shopify", "target": "wiki:tobias-lutke", "type": "references", "note": "engineering leadership behind the project" }, { "source": "wiki:shopify", "target": "wiki:jarred-sumner", "type": "references", "note": "autonomous optimization projects" }, { "source": "wiki:shopify", "target": "wiki:simon-willison", "type": "references", "note": "developer tooling community" }, { "source": "wiki:shota-sawada", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:shota-sawada", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:shreya-shankar", "target": "wiki:hamel-husain", "type": "references", "note": null }, { "source": "wiki:shreya-shankar", "target": "wiki:error-analysis-and-evals", "type": "references", "note": null }, { "source": "wiki:shreya-shankar", "target": "wiki:automated-eval-engineering", "type": "references", "note": null }, { "source": "wiki:shreya-shankar", "target": "wiki:closed-loop-agent-improvement", "type": "references", "note": null }, { "source": "wiki:sida-peng", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:sida-peng", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:simon-willison", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": ", arguing that writing code has become cheap while software quality, verification, and maintainability remain the primary engineering constr" }, { "source": "wiki:simon-willison", "target": "wiki:agentic-code-quality", "type": "references", "note": "verification controls" }, { "source": "wiki:simon-willison", "target": "wiki:red-green-tdd", "type": "references", "note": "test-driven loops" }, { "source": "wiki:simon-willison", "target": "wiki:agentic-manual-testing", "type": "references", "note": "dynamic verification" }, { "source": "wiki:simon-willison", "target": "wiki:addy-osmani", "type": "references", "note": "contemporary in developer tooling" }, { "source": "wiki:steve-freeman", "target": "wiki:nat-pryce", "type": "references", "note": "of \"Growing Object Oriented Software\" who adopted alistair-cockburn's hexagonal-architecture pattern. His work helped popularize the Ports a" }, { "source": "wiki:steve-freeman", "target": "wiki:hexagonal-architecture", "type": "references", "note": "adopted and promoted Cockburn's pattern" }, { "source": "wiki:steve-freeman", "target": "wiki:clean-architecture", "type": "references", "note": "his work contributed to the architectural synthesis" }, { "source": "wiki:stripe", "target": "wiki:agentic-code-quality", "type": "references", "note": "verification controls" }, { "source": "wiki:stripe", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": "browser verification patterns" }, { "source": "wiki:stripe", "target": "wiki:anthropic", "type": "references", "note": "collaboration on agent evals" }, { "source": "wiki:stripe", "target": "wiki:openai", "type": "references", "note": "evaluation targets" }, { "source": "wiki:tatsuya-shirai", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:tatsuya-shirai", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:tessl", "target": "wiki:agentic-code-quality", "type": "references", "note": "feedback signal tiers and verification gates" }, { "source": "wiki:tessl", "target": "wiki:agent-harness-engineering", "type": "references", "note": "composite system harness design" }, { "source": "wiki:tessl", "target": "wiki:designing-for-verifiability", "type": "references", "note": "objective verification criteria over reference solutions" }, { "source": "wiki:tessl", "target": "wiki:error-analysis-and-evals", "type": "references", "note": "benchmark and eval methodology" }, { "source": "wiki:tobias-lutke", "target": "wiki:shopify", "type": "references", "note": "company context for the optimization work" }, { "source": "wiki:tobias-lutke", "target": "wiki:jarred-sumner", "type": "references", "note": "autonomous optimization projects" }, { "source": "wiki:tobias-lutke", "target": "wiki:simon-willison", "type": "references", "note": "developer community" }, { "source": "wiki:trygve-reenskaug", "target": "wiki:james-coplien", "type": "references", "note": "of DCI (Data, Context, and Interaction) architecture. His work on DCI patterns contributed to the architectural thinking that robert-c-marti" }, { "source": "wiki:trygve-reenskaug", "target": "wiki:clean-architecture", "type": "references", "note": "his DCI work influenced the synthesis" }, { "source": "wiki:tue-le", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:tue-le", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:vercel", "target": "wiki:model-provider-abstraction", "type": "references", "note": ": adapters exist for Anthropic, OpenAI, and any OpenAI-compatible endpoint including local models." }, { "source": "wiki:vercel", "target": "wiki:llm-message-protocol", "type": "references", "note": "and structured-outputs concepts." }, { "source": "wiki:vinicius-carvalho-lopes", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:vinicius-carvalho-lopes", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:viv-trivedy", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:viv-trivedy", "target": "wiki:context-engineering", "type": "references", "note": null }, { "source": "wiki:viv-trivedy", "target": "wiki:multi-agent-orchestration", "type": "references", "note": null }, { "source": "wiki:wes-mckinney", "target": "wiki:agentic-software-factory", "type": "references", "note": "operating model for autonomous code generation and verification" }, { "source": "wiki:wes-mckinney", "target": "wiki:agentic-code-quality", "type": "references", "note": "multi-tier verification and constraint-driven backpressure" }, { "source": "wiki:wes-mckinney", "target": "wiki:generator-evaluator-loop", "type": "references", "note": "separating generator models from reviewer models" }, { "source": "wiki:wes-mckinney", "target": "wiki:agent-harness-engineering", "type": "references", "note": "system harness orchestration and tooling" }, { "source": "wiki:wilson-lin", "target": "wiki:multi-agent-orchestration", "type": "references", "note": null }, { "source": "wiki:wilson-lin", "target": "wiki:agent-harness-engineering", "type": "references", "note": null }, { "source": "wiki:wilson-lin", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:xinye-zhao", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:xinye-zhao", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:yanjun-zhang", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:yanjun-zhang", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:yi-liu", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:yi-liu", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:ying-zhang", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:ying-zhang", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:yubin-qu", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:yubin-qu", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:yuekang-li", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:yuekang-li", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:yutaro-kashiwa", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:yutaro-kashiwa", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:ziqian-zhong", "target": "wiki:agentic-code-quality", "type": "references", "note": "empirical implications for factory quality controls" }, { "source": "wiki:ziqian-zhong", "target": "wiki:agentic-quality-evidence", "type": "references", "note": "comparison of benchmark, field, and controlled evidence" }, { "source": "wiki:agentic-quality-evidence", "target": "wiki:agentic-code-quality", "type": "references", "note": null }, { "source": "wiki:agentic-quality-evidence", "target": "wiki:addy-osmani", "type": "references", "note": ", simon-willison). | 19% task completion slowdown in experienced devs on familiar repos; perceived vs actual speed gap.^[raw/papers/metr-dev" }, { "source": "wiki:agentic-quality-evidence", "target": "wiki:kent-beck", "type": "references", "note": "). | Agents frequently engage in test-softening, test deletion, or author self-fulfilling tests.^[raw/papers/tests-agentic-pull-requests-202" }, { "source": "wiki:agentic-quality-evidence", "target": "wiki:eval-driven-development", "type": "references", "note": "eval methodology" }, { "source": "wiki:agentic-quality-evidence", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": "practitioner patterns" }, { "source": "wiki:agentic-quality-evidence", "target": "wiki:agent-containment-and-blast-radius", "type": "references", "note": "authorization boundaries" }, { "source": "wiki:agentic-code-quality-cycle-2-entity-accounting", "target": "wiki:airbnb", "type": "references", "note": "organization entity. |" }, { "source": "wiki:agentic-code-quality-cycle-2-entity-accounting", "target": "wiki:stripe", "type": "references", "note": null }, { "source": "wiki:agentic-code-quality-cycle-2-entity-accounting", "target": "wiki:agentic-code-quality", "type": "references", "note": null }, { "source": "wiki:agentic-code-quality-cycle-2-entity-accounting", "target": "wiki:agentic-quality-evidence", "type": "references", "note": null }, { "source": "wiki:agentic-code-quality-cycle-2-entity-accounting", "target": "wiki:eval-driven-development", "type": "references", "note": null }, { "source": "wiki:agentic-code-quality-cycle-2-entity-accounting", "target": "wiki:agentic-engineering-patterns", "type": "references", "note": null }, { "source": "wiki:agentic-code-quality-entity-accounting", "target": "wiki:aditi-raghunathan", "type": "references", "note": ", ahmed-e-hassan, andrei-botocan, beatrice-casey, beth-barnes, brittany-reid, christoph-csallner, david-gros, david-rein, dipayan-banik, dun" }, { "source": "wiki:agentic-code-quality-entity-accounting", "target": "wiki:model-evaluation-and-threat-research", "type": "references", "note": "owns two ingested capability/productivity sources." }, { "source": "wiki:agentic-code-quality-entity-accounting", "target": "wiki:epoch-ai", "type": "references", "note": "owns the ingested SWE-bench Verified analysis." }, { "source": "wiki:agentic-code-quality-entity-accounting", "target": "wiki:dora", "type": "references", "note": "owns the ingested organizational research report." }, { "source": "wiki:agentic-code-quality-entity-accounting", "target": "wiki:openai", "type": "references", "note": "existing entity; owns the ingested SWE-bench Verified audit." }, { "source": "wiki:agentic-code-quality-entity-accounting", "target": "wiki:agentic-code-quality", "type": "references", "note": null }, { "source": "wiki:agentic-code-quality-entity-accounting", "target": "wiki:agentic-quality-evidence", "type": "references", "note": null }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:addy-osmani", "type": "references", "note": "writer on agent harness engineering and conductor/orchestrator workflows" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:anthropic", "type": "references", "note": "AI company publishing production research on agent harnesses and multi-agent systems" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:armin-ronacher", "type": "references", "note": "software developer writing about shared understanding and architectural coherence" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:cursor", "type": "references", "note": "AI coding company experimenting with long-running multi-agent development" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:james-shore", "type": "references", "note": "software-development writer analyzing AI productivity through maintenance costs" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:jarred-sumner", "type": "references", "note": "Bun creator; led the agent-assisted Zig-to-Rust port" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:johann-rehberger", "type": "references", "note": "security researcher on prompt injection and normalization of deviance in AI" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:lalit-maganti", "type": "references", "note": "Syntaqlite creator documenting AI's implementation/design boundary" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:mario-zechner", "type": "references", "note": "software developer critiquing cognitive debt from unchecked agentic coding" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:shopify", "type": "references", "note": "software company whose Liquid project supplied an autoresearch optimization case study" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:tobias-lutke", "type": "references", "note": "Shopify co-founder; applied autoresearch loops to Liquid optimization" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:viv-trivedy", "type": "references", "note": "credited by Addy Osmani with naming harness engineering and articulating the model-plus-harness framing" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:wilson-lin", "type": "references", "note": "Cursor researcher documenting planner-worker coordination for long-running coding agents" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:simon-willison", "type": "references", "note": "expanded with additional agentic engineering patterns and guides" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:andrej-karpathy", "type": "references", "note": "updated with coding-conduct and pedagogy layer attribution" }, { "source": "wiki:agentic-engineering-entity-accounting", "target": "wiki:llm-wiki-ecosystem-analysis", "type": "references", "note": "by demonstrating entity accounting practices and the agent-harness-engineering concept development through documented contributor attributio" }, { "source": "wiki:llm-wiki-ecosystem-analysis", "target": "wiki:llm-wiki-pattern", "type": "references", "note": null }, { "source": "wiki:llm-wiki-ecosystem-analysis", "target": "wiki:context-engineering", "type": "references", "note": "the wiki as compiled agent context" }, { "source": "wiki:llm-wiki-ecosystem-analysis", "target": "wiki:andrej-karpathy", "type": "references", "note": "the pattern's author" }, { "source": "wiki:llm-wiki-ecosystem-analysis", "target": "wiki:error-analysis-and-evals", "type": "references", "note": "evidence linting as an eval gate" } ] }