Thinking

Notes from the lab.

Essays, opinions, and technical notes on AI agents, MCP servers, LLM engineering, and shipping software that works.

  1. Building your first MCP server.

    A practical guide to building a Model Context Protocol server that gives Claude typed, auditable access to your APIs and databases.

    Read →
  2. How to choose between Claude Code, Codex, and Cursor in 2026.

    Three different tools, three different theories of what AI-assisted coding should be. Here is how to pick the one that fits your team.

    Read →
  3. Claude Code vs. the rest: a working comparison.

    We have used Claude Code, Cursor, GitHub Copilot, and Codex in production. Here is what we actually think.

    Read →
  4. Evals before vibes.

    How do you know your AI feature is working? Most teams go by feeling. The right answer is a small eval set that catches regressions before they ship.

    Read →
  5. Prompts need version control.

    A prompt that worked yesterday can break tomorrow. Without history, you cannot know what changed, what regressed, or how to roll back.

    Read →
  6. Build the thing you wish existed.

    We run our own products first, then take client work with fewer assumptions and sharper opinions.

    Read →
  7. Ship the workflow before the pitch.

    The fastest way to lose a technical client is to demo something that doesn't exist. Ship the workflow as a working prototype first.

    Read →

Have something to build?

Start a project → See the work →