Life in Pixels, replayed.
Six months of my own daily data, askable in plain language. Below are the twenty-six questions from the eval, played back one real run at a time: what the router decided, which days it pulled or computed, the answer it wrote, and what the validator said about it before anything was shown.
Nothing on this page is live. Every run is copied from evals/results/2026-09-22.json in the repo, and the data behind it is a seeded synthetic export shaped like mine, because mine stays on my machine. The answers are the model's, as recorded; when the validator disagreed with one, you will see that too.
In plain terms: you pick a question, and you watch the tool decide what kind of question it is, find the right days, write an answer, and then check its own answer before showing it.
01Pick a question, read the trace
two steps are model calls, two are code, and the code gets the last word02What a weekly rollup chunk changed, and what it did not
In plain terms: adding week-long summaries fixed the one question about a whole week and left every other answer the same.
03The same pipeline as an MCP server
The router, the validator and the model call are exposed over stdio as a local MCP server with two read-only tools, so Claude Desktop and Claude Code can ask the data questions while it never leaves the machine. There is no write tool, on purpose. The config and the two tool schemas are in the repo.