decide.js asks ~10 choice questions in one call (mark, x, measure, agg, series,
order, top, one filter per text column) and assembles the spec; the validator
still checks it. Weakest needed answer < FLOOR, a failed check or a model error
hands the question to the LLM path, and the response says why. Page: brain
picker, latency/confidence line, 'or as <mark>' from the mark probabilities.
bench.py scores brains on 12 fixed questions.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VDkN7ukK1kXkqov8FaZxva
Claude