Skip to content

Concept Map

All site content grouped by theme, cutting across sections. Find related concepts regardless of where they live in the navigation.

This map cuts across the directory tree to reflect the practitioner-resource spine — patterns, anti-patterns, paper summaries, and tool features sit together when they're about the same problem. See the Tags index for topic-tag entry points or STANDARDS.md for what makes the cut.

  • Context Engineering


    Budgets, compression, attention, and retrieval

    Jump to section →

  • Instructions & Prompts


    Layering, scoping, polarity, and instruction files

    Jump to section →

  • Agent Architecture


    Composition, delegation, coordination, and memory

    Jump to section →

  • Tool Design


    Descriptions, discovery, filtering, and engineering

    Jump to section →

  • Security & Safety


    Injection defense, sandboxing, and credentials

    Jump to section →

  • Testing & Evaluation


    Evals, metrics, code review, and verification

    Jump to section →

  • Hooks & Guardrails


    Lifecycle events and deterministic enforcement

    Jump to section →

  • Reliability & Recovery


    Error handling, cost control, and loop detection

    Jump to section →

  • Standards & Protocols


    AGENTS.md, MCP, A2A, and interop conventions

    Jump to section →

  • Development Workflows


    Planning, bootstrapping, CI/CD, and iteration

    Jump to section →

  • Human Factors


    Cognitive load, attention management, and adoption

    Jump to section →

  • Anti-Patterns


    Common mistakes with context, prompts, and trust

    Jump to section →

  • Emerging Concepts


    Product-as-IDE, personalization, and early signals

    Jump to section → - Discoverability & GEO


    Generative-engine optimisation, llms.txt, and topical authority — making content reachable by AI answer engines.

    Jump to section →

  • Frameworks


    Multi-page framework syntheses — end-to-end agent operating models and migration playbooks.

    Jump to section →

  • Learning & Training


    Structured curriculum modules and hands-on tracks for agent-assisted development.

    Jump to section →

  • Tool-Specific Guides


    Tool-specific features and workflows for Claude Code, GitHub Copilot, Cursor, and other assistants.

    Jump to section →

Context Engineering

Managing what enters the context window — budgets, compression, attention, and retrieval.

Instructions & Prompts

Writing effective instructions — layering, scoping, polarity, and instruction file conventions.

Agent Architecture

Composing, structuring, and coordinating agents — delegation, composition patterns, multi-agent coordination, and memory.

Tool Design

Building, describing, and filtering tools — making tools agent-friendly.

Security & Safety

Defending against prompt injection, data exfiltration, and credential exposure.

Testing & Evaluation

Measuring agent quality — evals, metrics, code review, and verification strategies.

Hooks & Guardrails

Deterministic enforcement — lifecycle hooks, permissions, and structured constraints.

Reliability & Recovery

Error handling, cost control, and recovery — circuit breakers, rollbacks, loop detection, and performance budgets.

Standards & Protocols

Open standards and conventions for agent interoperability — AGENTS.md, MCP, A2A, and more.

Development Workflows

End-to-end processes — planning, bootstrapping, CI/CD integration, and team adoption.

Human Factors

The human side — cognitive load, attention management, supervision, and team dynamics.

Anti-Patterns

What to avoid — common mistakes and why they fail.

Emerging Concepts

Fringe ideas not yet standardized — early signals worth watching.

Discoverability & GEO

Generative-engine optimisation, llms.txt, and topical authority — making content reachable by AI answer engines.

Frameworks

Multi-page framework syntheses — end-to-end agent operating models and migration playbooks.

Learning & Training

Structured curriculum modules and hands-on tracks for agent-assisted development.

Tool-Specific Guides

Tool-specific features and workflows for Claude Code, GitHub Copilot, Cursor, and other assistants.

Feedback