Capability 02 of 04 · Organization
Knowledge Management
How institutional knowledge is captured, shared, and made available to both humans and agents.
5
maturity levels
15
practices
15
guides
L1 · Stage 01Assisted
Practices - what it looks like3 guides
- Processes passed on verbally, not documentedFolk tradition knowledge is the undocumented institutional lore that accumulates around every long-lived codebase.guide→
- Little written documentationThe documentation chicken-and-egg problem is one of the most persistent failure modes in software organizations.guide→
- Key knowledge held by senior staffThe architecture, the history and the dangerous edge cases live in two or three people's heads. Everything looks fine until one of them is unavailable.guide→
Criteria - what to measure
- 01The team has working knowledge of its systems
- 02Onboarding includes a README or equivalent starting point
- 03Team acknowledges that tribal knowledge is a risk
- 04Some informal knowledge sharing exists (Slack threads, meeting notes)
L2 · Stage 02Delegated
Practices - what it looks like3 guides
- Docs refresh initiativeA docs refresh initiative is the structured, time-boxed effort to bring existing documentation back into alignment with reality.guide→
- Architecture Decision Records (ADRs)Short records of why a technical decision was made: the context, the options considered and the consequences accepted, not just the choice itself.guide→
- Written onboarding pathsA written onboarding path is a structured, step-by-step guide that takes a new engineer from zero access to productive contribution on a specific codebase or team.guide→
Criteria - what to measure
- 01Documentation refresh initiative is active with measurable progress
- 02The team writes a decision record when it chooses an architecture or a major dependency
- 03Written onboarding path exists (new developer can self-serve key setup steps)
- 04ADRs are indexed and searchable
- 05Onboarding path has been validated by at least one new hire completing it solo
L3 · Stage 03Systematic
Practices - what it looks like3 guides
- Documentation = infrastructure (not an HR problem)Most engineering organizations treat documentation as a people problem: if engineers wrote better docs, if seniors were more generous with their knowledge, if new hires asked more questions.guide→
- Lint rules > docs (enforced > suggested)Documentation that says "we use camelCase for variable names" is a suggestion.guide→
- A queryable map of the codebase (structure, ownership, change history); agentic search and plain-text memory over vector databasesThe repository becomes a queryable graph of calls, dependencies, owners and tests, so "what breaks if I change this interface?" has a real answer.guide→
Criteria - what to measure
- 01Documentation is treated as infrastructure (owned by engineering, not HR or PMO)
- 02Lint rules enforce conventions rather than relying on documentation alone (enforced > suggested)
- 03A queryable map of the codebase (structure, ownership, change history) is operational
- 04Documentation freshness is tracked (pages older than 90 days are flagged for review)
- 05Knowledge graph is integrated with agent context pipeline (agents query it at runtime)
L4 · Stage 04GovernedMost teams aim here
Practices - what it looks like3 guides
- Context Fabric: MCP servers feed agents automatically, discoverable and assessable from published metadata before a client ever connectsThe MCP servers an organization runs to feed agents context automatically, discoverable and assessable from published metadata before a client ever connects.guide→
- Skills and MCP servers packaged once and installed across clients as vendor-neutral plugins, then treated as maintained assets with a review cadence and an eviction rule - installing a useful skill and keeping it forever are separate decisionsThe agent turns a vague ticket into a structured spec, and the skills and MCP servers it runs on are packaged once as vendor-neutral plugins and kept as maintained assets with a review cadence and an eviction rule.guide→
- Docs auto-updated by agents on code changeA code change triggers the doc change: the signature moves and the API reference moves with it, rather than waiting for someone to remember.guide→
Criteria - what to measure
- 01Context Fabric: MCP servers automatically feed institutional knowledge to agents
- 02Autonomous Requirements pipeline: unclear tickets are auto-expanded into specs with acceptance criteria
- 03Agents auto-update documentation when code changes (no manual doc maintenance)
- 04Context Fabric covers 80%+ of active repositories
- 05Doc auto-update PRs are reviewed and merged within 24 hours
L5 · Stage 05Self-improving
Practices - what it looks like3 guides
- Self-evolving knowledge baseA self-evolving knowledge base is a knowledge infrastructure that improves itself without requiring humans to initiate updates.guide→
- The written record is kept current by agents: drift is detected, corrected and validatedThe organisation's written record is kept current by agents rather than by anyone's good intentions: drift from reality is detected, corrected, and the correction is validated before it is trusted.guide→
- Organizational memory = Git-backed, agent-readable, always currentThe knowledge that used to live in senior engineers' heads becomes Git-backed, agent-readable and current enough that agents can act on it.guide→
Criteria - what to measure
- 01Knowledge base is self-evolving (agents add, update, and validate knowledge entries continuously)
- 02Agent detects stale context, updates it, and validates the update - without human initiation
- 03Organizational memory is Git-backed, agent-readable, and provably current
- 04Knowledge base freshness score exceeds 95% (% of entries updated within their defined freshness window)
- 05Self-evolving updates are validated against codebase to prevent knowledge drift
From the Field
Recent releases, projects and discussions the AI Radar classified into this capability.
discussion
How to deal with a coworker who thinks he can make all the software decisions
discovered
AI-first knowledge base and startup OS
article
OpenAI Unveils GPT-5.3 Instant
discovered
danvega/karpathy-wiki
discovered
Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.
article
DevResolve – AI chat widget that answers technical questions from your docs
discovered
Search, archive, and recall your AI conversations. ChatGPT, Claude, Gemini, Grok, Kimi. Local-first, MIT licensed.
discovered
MarkdownAI - live documents powered by directives
Which level is your team at in Knowledge Management?
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 Organization.
Start the assessment →