RAG & SearchRAGCitationsFixed budget
Build a RAG Support Agent for a Legal SaaS
Northwind Legal Cloud · Austin, TX
$12k fixed
The outcome
The agent answers customer questions grounded in 4,000+ pages of contract law docs — with citations, so support reps trust every reply.
The client
Northwind Legal Cloud — Austin, TX. A rag & search build we delivered end to end.
The challenge
Ship a retrieval-augmented support agent over their document corpus: chunk and embed the knowledge base, wire up hybrid search, and return cited answers inside their existing help widget.
What we built
- Stand up an ingestion pipeline for their docs, tickets, and policy PDFs
- Build hybrid (vector + keyword) retrieval with citation-backed responses
- Add eval harness + guardrails so the agent refuses when unsure
The stack
Stack: Python or TypeScript, a vector DB (pgvector/Pinecone), an LLM API, and solid RAG eval chops.
Want something like this?
Tell us what you're building and we'll scope it — most projects start within a week.