Capability 02 of 04 · Development
Context Engineering
What information agents receive about your codebase, architecture, and conventions.
5
maturity levels
15
practices
15
guides
L1 · Stage 01Assisted
Practices - what it looks like3 guides
- Agent works from the currently open fileWhy AI agents at L1 are flying blind - they see only the open file, with no awareness of your project's architecture, conventions, or dependencies.guide→
- Project knowledge lives with people, not docsAt L1, the rules governing your codebase live in developers' memories - invisible to AI agents, fragile under turnover, and impossible to scale.guide→
- Onboarding leans on the existing README and peopleStale documentation is more than a developer experience problem - it actively prevents AI agents from using docs as context and signals that the team hasn't invested in machine-readable knowledge.guide→
Criteria - what to measure
- 01The agent can read the file(s) the developer is working on
- 02Developers can supply the agent with project context when needed
- 03README.md exists (may be incomplete)
- 04Developers manually paste context into AI chat when needed
L2 · Stage 02Delegated
Practices - what it looks like3 guides
- CLAUDE.md pruned to repo-specific gotchas and committed to the repo (repos without committed agent config saw twice the cognitive-complexity growth: +53% vs +27%)A lean, repo-specific CLAUDE.md committed to version control is the single highest-leverage context engineering investment - it gives every AI agent the minimum viable information about what your project is and how it works.guide→
- Written coding conventionsDocumenting your team's semantic coding decisions - not just style rules - gives AI agents the judgment framework they need to suggest code that fits your architecture, not just code that compiles.guide→
- Agent instruction files + Skills as the unit of reuse (SKILL.md alongside CLAUDE.md, AGENTS.md, llms.txt; cross-agent registries)Agent instruction files - CLAUDE.md, .cursorrules, copilot-instructions.md - have become a standard software project artifact, with 60,000+ repositories on GitHub already containing them.guide→
Criteria - what to measure
- 01CLAUDE.md or equivalent exists with project description, tech stack, and top conventions
- 02Written coding conventions document exists and is referenced from agent instruction files
- 03Agent instruction files are committed to the repository (not local-only)
- 04CLAUDE.md includes explicit prohibitions (banned libraries, anti-patterns)
- 05Agent instruction files are reviewed as part of the standard PR process
L3 · Stage 03Systematic
Practices - what it looks like3 guides
- Architecture, ownership and operational context reach the agent through governed servers rather than pasted textModel Context Protocol servers are the infrastructure layer of context engineering at L3 - dedicated services that give AI agents structured, real-time access to your organization's knowledge.guide→
- Retrieval is deterministic and cheap: the agent searches and extracts on demand instead of being fed a pre-built indexRetrieval is deterministic and cheap: the agent searches and extracts what it needs on demand, rather than being fed a pre-built index that was assembled before anyone knew what the task was.guide→
- Context budgeting with a standing eviction rule: agent files are audited and cut, not only appended (lint leakage 62%, context bloat 42%, skill leakage 35% across 100 repos; Anthropic cut >80% of Claude Code's system prompt with no measurable quality loss)AI models have finite context windows - context budgeting is the practice of deliberately allocating that budget across context types, and evicting from it on a schedule, to maximize agent effectiveness per token spent.guide→
Criteria - what to measure
- 01MCP servers provide structured context (architecture, ownership, SLAs) to agents
- 02Context is organized across at least 3 of the 5 levels: System, Code, Org, Historical, Operational
- 03Token budget management is implemented (agents receive context within defined token limits)
- 04Context sources are versioned and tested for correctness
- 05Context budgeting policy defines priority order when token limits are reached
L4 · Stage 04GovernedMost teams aim here
Practices - what it looks like3 guides
- BYOC: org PUSHES context to the agentAt L4, organizations flip the context model - instead of agents pulling context on demand, the org pre-assembles and pushes a rich context package to agents at task start, eliminating discovery latency and ensuring consistency.guide→
- A queryable map of code structure, ownership and change historySemantic knowledge graphs of codebases - built by tools like Graph Buddy and CodeTale - give AI agents structural understanding of your codebase without requiring them to read every file.guide→
- Spec-Driven Development: AGENTS.md as shared spec interface (Spec Kit constitution.md, Andrew Ng + JetBrains, Thoughtworks)At L4, AI agents transform Jira or Linear tickets into structured specifications and failing acceptance tests before a developer touches the implementation - creating a context artifact that guides the entire downstream workflow.guide→
Criteria - what to measure
- 01Organization pushes context to agents automatically (BYOC - Bring Your Own Context)
- 02A queryable map of code structure and ownership is integrated with the agent context pipeline
- 03Ticket-to-spec automation generates acceptance tests from requirements without manual writing
- 04Context push triggers on repository events (commit, PR, deploy) without manual refresh
- 05Knowledge graph covers 80%+ of active repositories
L5 · Stage 05Self-improving
Practices - what it looks like3 guides
- Persistent agent identity + memory (Beads/Git, Open Memory Protocol; treat auto-memory as an exfiltration surface - "Memory Heist")At L5, agents maintain persistent identity and memory across sessions using structured memory files committed to git - accumulating codebase-specific institutional knowledge that makes them progressively more effective over time.guide→
- Production telemetry → context auto-updateAt L5, agent context updates automatically based on production signals - when a service degrades, agents working on related code receive updated operational context without manual intervention.guide→
- Stale context is detected and refreshed before an agent runs on itContext is verified against reality at the moment it is about to be used: stale material is detected and refreshed before the agent runs on it, rather than after the mistake it caused.guide→
Criteria - what to measure
- 01Agents maintain persistent identity and memory across sessions (Beads/Git-backed)
- 02Production telemetry feeds back into agent context automatically (deploy, error, performance data)
- 03Context that has gone stale is detected and refreshed before an agent runs on it
- 04Agent memory persists architectural decisions and their rationale across sessions
- 05Self-healing context updates are validated by automated tests before commit
From the Field
Recent releases, projects and discussions the AI Radar classified into this capability.
release
topoteretes/cognee
article
Anthropic Removed MagicDocs from Claude Code
discovered
Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own session history to
discovered
Model-agnostic code memory MCP server. Budget-aware graph retrieval for AI agents. Sub-millisecond queries, token budgeting, deterministic results. Built o
discovered
Practical OpenClaw tips for memory, reliability, cost, automation, and multi-agent workflows.
discovered
Comprehensive guide to AI agent engineering: how 30+ frameworks actually work under the hood. Context rot, compaction, system prompt assembly, SOUL.md, age
discovered
A fast codebase indexer and MCP server for AI coding agents.
discovered
SUPERCHARGE AI-assisted development by using Git. Cross-model review gates, evidence-linked closure, verification profiles, model-tier routing, artifact envelopes, an
Which level is your team at in Context Engineering?
The criteria above are what we check in a facilitated assessment. Run it yourself to place this capability, see which gates you have passed, and compare it against the other 3 in Development.
Start the assessment →