# Context Management Maturity Model A framework for assessing how sophisticated an individual, team, or organization is at managing AI context. Combines [[Levels of AI Context Management]] (individual progression) with [[Levels of AI use]] (tool adoption) into a unified maturity view that spans all three layers: [[Personal Context Management (PCM)|PCM]], [[Team Context Management (TCM)|TCM]], and [[Enterprise Context Management (ECM)|ECM]]. ## Maturity dimensions | Dimension | Immature | Mature | |---|---|---| | **Context scope** | Ad-hoc prompts per conversation | Structured, persistent context across all interactions | | **Context lifecycle** | Static, set-and-forget | Actively maintained, reviewed, and evolved | | **AI memory** | None or built-in only | Managed, curated, and auditable memory systems | | **Skills and procedures** | Repetitive manual instructions | Codified skills that standardize outputs | | **Context sharing** | Individual silos | Layered sharing (PCM → TCM → ECM) | | **Context governance** | No policies | Clear policies on what context AI can access | | **Feedback loops** | None | Agents learn from outcomes and update context | ## Assessment questions - Do you repeat yourself to AI? (context persistence) - Does AI know your goals, not just your current question? (context depth) - Can a new team member's AI get productive immediately? (TCM maturity) - Is there an org-wide policy for AI context access? (ECM maturity) - Do your agents improve their own context over time? (ACE maturity) ## References - ## Related - [[Levels of AI Context Management]] - [[Levels of AI use]] - [[Personal Context Management (PCM)]] - [[Team Context Management (TCM)]] - [[Enterprise Context Management (ECM)]] - [[Context Engineering]] - [[Agentic Context Engineering]] - [[AI Master Prompt]]