Review Queue — internal access only
Search by ticker. Edit cells inline, set Action to Duplicate or Delete, then click Save Changes. All writes go directly to the live database.
| Action | Drug | Indication | Stage | PDUFA | PDUFA✓ | Cat. Date | Short Note | Long Note | Active | Last Updated |
|---|---|---|---|---|---|---|---|---|---|---|
All changes written automatically to drug_assets — from 8-K extractions and OpenFDA polling. Spot-check for errors; use ↩ Undo to revert any bad write.
| Date | Ticker | Drug | Indication | Before | After | Source | |
|---|---|---|---|---|---|---|---|
Summary stats for each completed update.py run — hourly Railway cron and manual runs.
| Execution (ET) | Mode | Companies | Filings | New | → Haiku | → Sonnet | Auto-Applied | Queued | OpenFDA | Errors | Elapsed |
|---|---|---|---|---|---|---|---|---|---|---|---|
Execution — when the run started (ET)
Mode — normal / force-backfill / openfda-only / 8k-only (local if manual)
Companies — total companies scanned
Filings — all 8-K/6-K filings found by EDGAR in the lookback window
New — filings not yet marked was_processed=1 (= Filings − already processed)
→ Haiku — new filings that passed the keyword pre-filter → LLM relevance screen
→ Sonnet — Haiku-screened filings deemed relevant and sent for full extraction
Auto-Applied — updates written directly to drug_assets (high confidence)
Queued — updates routed to proposed_updates for human review
OpenFDA — FDA approvals matched via OpenFDA API
Errors — per-company exceptions during scan
Elapsed — total wall-clock runtime in minutes
Audit log of press release headlines processed by the Yahoo RSS poller. Headlines with genuinely new info flow into the Pipeline Queue as proposed updates.