Project case study

Full-Stack AI Chatbot

Secure AI assistant workspace with authentication, file ingestion, and retrieval-backed chat for business knowledge workflows.

Key outcomes

  • Implemented JWT and OAuth2-based authentication for protected user sessions.
  • Added file upload and retrieval workflows to ground model responses in uploaded knowledge.
  • Connected a responsive chat interface to real-time LLM conversations through OpenRouter.

This project combined product usability with production concerns. The goal was not only to make an LLM chat interface work, but to make it secure, stateful, and useful for real internal knowledge tasks.

I worked across the stack, shaping backend APIs, data persistence, and the web experience so the system could handle authenticated users, uploaded files, and retrieval-backed conversations in one coherent flow.