Sheet 05 — Field notes

Writing

Notes from things I am building. Mostly the unglamorous half of an AI system, the part that decides what gets indexed before anyone types a query.

07 notes on file

  1. Sheet 05.7

    How it was built

    Two projects in eleven days, built through Claude Code with one loop, four steps, and a person who writes the issues and says merge. The counts from the session transcripts, what the review caught, and what the person did.

  2. Sheet 05.6

    The view you license from

    A clip search over 300 public-domain films where every result opens the player at the frame it matched. Pick clips into a set and one page says what you would be paying for. The page's numbers, the ones that are good and the two that are not, and a sampling thesis the eval turned down.

  3. Sheet 05.5

    Where the page is ahead of the tool

    The same clip search answers a person through a page and an agent through three MCP tools. One query run both ways, and a list of what the person gets that the agent cannot reach yet. The tools have a few things the page lacks too.

  4. Sheet 05.4

    The grader that charges for confidence

    Ten incidents scripted into a real Honeycomb environment, with the true cause in a file the agent never sees. A grader that scores the answer, and takes more off a wrong answer said with confidence than a wrong one said with doubt. Thirty of thirty right on one model. Six of thirty on another that passes the vendor's own process check.

  5. Sheet 05.3

    The budget that measured itself

    A trace of one request, stage by stage, is what explained a bad number. A search timeout had moved from eight seconds to fifteen on the strength of one measurement, and within ninety seconds of the deploy two searches were cancelled at fifteen point one.

  6. Sheet 05.2

    Two stores, one eval

    A clip search app's 264,626 frame vectors, kept in Postgres all project, written a second time to object storage and asked the same hundred questions through the same route. The answers matched and the price of a query moved. Then a commercial video model went in as a third column, over the slice its free tier would hold.

END OF INDEX

The builds these notes come from

Every note here is downstream of something on the work sheet.