Insights

Notes from building memory for AI agents.

Field write-ups on what actually works when you wire an AI coding agent to an external memory layer. Two formats: deep technical guides for the full picture, short problem-solution answers for a specific intent.

Deep guides

1 article

Long-form technical articles. The full thesis, the trade-offs, the honest limits. For builders who want to understand the architecture, not just the answer.

  1. Deep guide

    AI engineering · 2026-05-26 · 11 min read

    How to stop context loss in Claude Code: an operational memory approach

    Why Claude Code keeps drifting, why bigger windows do not fix it, and how an operational memory layer with executable patterns and bounded stop conditions addresses it in practice.

Problem-solution guides

5 answers

Short, intent-driven answers for a specific question. Same operational substance as the deep guides, distilled to the action.

  1. Problem-solution

    Claude Code · 6 min read

    Claude Code keeps forgetting your project? Here is what fixes it.

    The short, operational answer to the Claude Code re-explanation tax: external memory with executable patterns, not a bigger context window.

  2. Problem-solution

    Cursor · 7 min read

    Cursor loses context on long projects. Here is the operational fix.

    Cursor drifts on real codebases — re-asks about files it edited an hour ago, violates conventions across modules. The fix is memory scoped to the repo and file, wired through MCP.

  3. Problem-solution

    Concept · 7 min read

    Operational memory for AI agents: what it is, what it is not.

    Not a vector database, not a chat history, not a long system prompt. A typed, bounded, per-tenant catalogue of executable patterns the agent retrieves contextually at execution time.

  4. Problem-solution

    Comparison · 7 min read

    Persistent memory vs long system prompts: which one should you actually use?

    Long prompts ship every turn. Persistent memory ships only what matches. The trade-offs, the failure modes of each, and when long prompts still win.

  5. Problem-solution

    Reliability · 8 min read

    How to make AI agent workflows reliable: executable patterns and stop conditions.

    Reliability is a property of the loop, not the model. Executable patterns the agent applies, and explicit stop conditions that bound where the agent can act on its own.

Deep guide = 3000+ words, full architecture and trade-offs. Problem-solution = short answer to a specific search intent. Both share the same operational substance.