Writing

Stories from the build log

Reflections on AI, product decisions, and the small stories that shape how we build.

  1. Making Hawkeye Claude-Ready

    Claude Haiku 5.5 couldn't run our Slack agent until we fixed one tool schema, and cost 4× until we turned on caching. Fixed, it still lost the classifier eval, and on a billed rerun it claimed work it never did.

    ai, llm, evaluation, agents

    22 min

  2. Why We Stayed on Luna 5.6

    The newer, cheaper model lost on our real-traffic evals. How we pick the model behind Hawkeye, our Slack PM agent, and the setting that beat switching.

    ai, llm, evaluation, agents

    18 min

  3. Beyond 95% Accuracy

    Whisper looked solved on benchmarks. Then doctors used it. What it took to make medical transcription hold up in noisy clinics and ORs.

    ai, healthcare, speech-recognition, machine-learning

    4 min

  4. Facts, Hypotheses, and the Art of Writing PRDs

    Every sentence in a PRD should either be a Fact or a Hypothesis. Avoid making Statements at all costs.

    product-management, writing, mentorship, prds

    3 min

  5. Beyond Accuracy

    Why evaluating LLM apps takes more than accuracy scores: trustworthiness, safety, reliability, and the habit of improving them continuously.

    ai, llm, machine-learning, product-management

    2 min

  6. The Secret to MCP Servers That LLMs Love Using

    LLMs don't use APIs the way developers do. Why most MCP servers frustrate agents, and how product thinking builds tools they actually use well.

    ai, mcp, product-management, llm

    5 min

  7. Beyond the Vacuum

    Exploring how original ideas emerge not from isolation, but from the rich interplay of diverse knowledge and experiences

    creativity, writing, personal-growth, originality

    2 min