mathiasandClaude Opus 4.8 aa918388b9 docs(brain): add two-column intent merge scaffold ...

Drop-in unified findings doc for the brain-MCP intent study. Locks the
shared row schema + closed intent vocab both columns must conform to.
Agent column filled from agent-intent-column.jsonl (46 acts, 37%
mismatch); human column left as PENDING cells + <<SYNTH>> blocks so the
Claude.ai-history analysis merges in without re-deriving structure.

Pre-seeds the cross-consumer divergence questions: agent mismatch is
write-side-heavy (supersede + verify-landed); hypothesis is human
mismatch is read-side-heavy (semantic + answer) — interface may fail the
two consumers at opposite ends.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-16 20:45:24 +02:00

..

eval

docs(eval): record M4 + M4b scorer runs — phase 2 gate cleared (infra#72)

2026-05-25 18:51:29 +02:00

raw

test: phase 1 integration smoke test passing

2026-04-17 21:18:08 +02:00

sessions

docs(brain): add two-column intent merge scaffold

2026-06-16 20:45:24 +02:00

training-data

feat: add protocols.md, retrospective discipline, and brain directory structure

2026-04-17 20:49:56 +02:00

wiki

test: phase 1 integration smoke test passing

2026-04-17 21:18:08 +02:00

schema.md

feat(pipeline): update system prompt for new LLM JSON contract (no slugs)

2026-04-23 19:45:21 +02:00