HR / OSPORTFOLIO WORKSPACE
hritikraj.dev/projects/supplierverse
All projectsImplemented · production evidence

SupplierVerse.ai

An AI procurement platform that turns fragmented public tenders into grounded, reviewable bid work across discovery, matching, collaboration, and response drafting.

85 FastAPI endpoints
LangGraphFastAPIAzure OpenAIPostgreSQLpgvector
01 / Case note

The operating problem

Procurement teams needed to find relevant tenders across seven inconsistent public portals, coordinate opportunity data, and draft answers without letting a model invent evidence.

02 / Case note

My contribution

Worked across the Next.js product, 85 FastAPI endpoints, 297 database migrations, ingestion jobs, matching, collaboration, billing, and shared identity boundaries. Built the Azure OpenAI and LangGraph Bid Writer flow around typed state and reviewable output.

03 / Architecture

System shape

Next.js workspaces + user JWT
85 FastAPI endpoints
LangGraph + Azure OpenAI
Postgres / pgvector + 297 migrations
7 procurement portal adapters
04 / Case note

The key decision

The Bid Writer uses a six-node graph with evidence allow-lists, claim provenance, critique loops, missing-input handling, and human insertion instead of autonomous submission.

05 / Case note

Reliability by design

Capture, normalisation, publication, enrichment, matching, explanation, feeds, and notifications are separate recoverable stages. SSE exposes progress without hiding failure.

06 / Evidence

What the source proves

2 active LangGraph workflows
297 database migrations
7 procurement adapters
Human-approved answer insertion
07 / Case note

Honest limits

The current audit does not establish broad production traffic, matching accuracy, or unattended scheduling for every source.

Have a hard problem?

Let’s build something
worth trusting.