Blog

Notes from building apps, shows and AI systems with a small team.

RSS
  1. How we ship software with AI agents without losing control

    Specs, small plans, task-scoped agents, independent review and real checks. How agents do the work while people keep the decisions.

  2. Routing between LLM providers to balance cost and quality

    Why we route requests across more than one model provider, how prompt caching cuts repeat costs, and why routing changes pass offline evals first.

  3. Designing AI memory that stays accurate

    Long-term memory for an AI companion is about keeping facts current, not storing more. Recall, supersession, and why contradictions cost trust.