Multisector
Augusta Labs
Matching 400,000+ companies to public funding.
An AI platform that matches Portuguese companies to public funding incentives.
I built the incentive extraction pipelines — collect each notice’s PDFs, parse and clean them, have an LLM extract dates, budgets and eligibility, merge per notice and fall back to a second pass to fill gaps — and loaded and indexed the 400k+ company profiles, 168 fields each with 24 years of revenue. Matching is company-first: shortlist by filters, then match eligibility within the shortlist.
- TypeScript
- Bun
- Hono
- PostgreSQL
- OpenAI
- Pinecone
- company profiles, loaded and indexed
- 400k+
- fields per company profile
- 168
- of revenue history per company
- 24 yrs
How it works
- PRR portalopen calls
- PT2030public notices
- collect PDFs
- parse & cleanbudget · date sections
- LLM extractiondates · budget · eligibility
- merge per noticenon-null wins
- LLM fallbackfills the gaps
- upsertPostgres
- search
- SQL filters
- vector search
- company shortlistfilters first
- incentive search
- eligibility matchquery ∩ shortlist
- results


