BreezeRFP
AI platform that helps companies win government contracts.
The problem
A contracting build (shipped as JustWin): an end-to-end SaaS for government-contracting teams. A Celery pipeline pulls solicitations from the SAM.gov API and an LLM matching algorithm ranks them by winnability. To respond, a LangChain + FAISS retrieval pipeline grounds an AI assistant (Claude 3.5 Sonnet and GPT-4o) in each company's knowledge base, drafting proposal outlines, cover letters, and FOIA requests straight from a lead's RFP documents. Vue 3 SPA on a Django + DRF backend.
The approach
A contracting build (shipped as JustWin): an end-to-end SaaS for government-contracting teams. A Celery pipeline pulls solicitations from the SAM.gov API and an LLM matching algorithm ranks them by winnability. To respond, a LangChain + FAISS retrieval pipeline grounds an AI assistant (Claude 3.5 Sonnet and GPT-4o) in each company's knowledge base, drafting proposal outlines, cover letters, and FOIA requests straight from a lead's RFP documents. Vue 3 SPA on a Django + DRF backend.
Highlights
- Celery workers ingest solicitations from the SAM.gov API and rank them by winnability with an LLM matching algorithm
- LangChain + FAISS RAG over each company's knowledge base grounds the AI assistant in their own past work
- Claude 3.5 Sonnet and GPT-4o draft proposal outlines, cover letters, and FOIA requests, plus a smart reader that distills long RFP PDFs
- Django + DRF API with PostgreSQL, Redis, and Stripe billing — deployed on Heroku with document storage on AWS S3
Tech stack
Want to talk through how this was built?
I build and ship production apps end-to-end. Happy to dig into the architecture, the tradeoffs, or your next project.