data+scoring: verbatim-source all policy_facts, recalibrate scorecard, fix recommendation 7081aaa rohitsar567 Claude Opus 4.7 (1M context) commited on May 16
refactor: KI-047 — bucket reorg (Option A safe subset) e2d09f9 rohitsar567 Claude Opus 4.7 (1M context) commited on May 14
docs: full sweep — fix stale model names + 48→62 fields + merge SUBMISSION 050823a rohitsar567 Claude Opus 4.7 (1M context) commited on May 14
Stack A: NIM brain + Maverick judge + Sarvam voice/Indic (D-019). Data moved to insurance-bot-data dataset; Space is now code-only. c32bddc verified rohitsar567 commited on May 13
Deploy v1 — single-Docker FastAPI + Next.js + RAG + voice + faithfulness f0adc52 verified rohitsar567 commited on May 13
rohitsar567 Claude Opus 4.7 (1M context) commited on 