Engine
How FINN works, and what it cost today.
Push
Filings in, a short brief out
- 01
Ingest
One market-wide NSE call per poll, filtered to your 18 and upserted on seq_id. A watermark with overlap self-heals gaps.
- 02
Classify
Rules on the subject first; GLM with a strict JSON schema only for what rules can't place, in batches of 10.
- 03
Score
Category weight × your weight × impact, clamped 0–100. Fraud or default is always Act.
- 04
Enrich
Results from the XBRL, people and deals from the PDF. Related filings collapse into one card.
- 05
Digest
Only ready cards, with source health — no 'caught up' unless every poll in the window succeeded.
Pull
Documents in, cited answers out
- 01
Documents
Annual reports and concall transcripts, fetched from an allowlist and checksummed.
- 02
Chunk
~500-token passages split at headings, page ranges kept, tables whole.
- 03
Embed
EmbeddingGemma-2 on Cloudflare Workers AI, 768 dimensions, task-prefixed.
- 04
Retrieve
Full-text and vector search fused by rank, always filtered to the one company.
- 05
Cite
Each quote must appear in its passage and each number in the passage or the filed facts — or it's flagged.
Today's meter
liveDeliberately not done
- Intraday prices — end-of-day bhavcopy only.
- News, broker notes and model memory on the research side — primary documents only.
- A composite 'credibility score' — the Promise Ledger reports a fraction with its denominator.
- OCR for scanned PDFs — they're flagged, not silently skipped.
- Multi-user accounts — the demo is open, with no sign-in.
- The BSE feed — NSE covers the portfolio.