Back to work
Case Study

SupportLens AI

SupportLens AI is a support inbox workflow for reviewing customer messages, checking policy context, preparing draft replies, and keeping approval in the hands of a human operator.

FastAPIPostgreSQLpgvectorGmail OAuthPII redaction
SupportLens AI reply workspace screenshot
Interactive Walkthrough

Step through the support workflow

SupportLens interactive screen
Inbox home with synced support messages and queue context.

Problem

Support teams jump between inboxes, policies, refund rules, shipping docs, warranty notes, and previous replies. The useful version needs evidence, privacy controls, and human approval before anything reaches a customer.

What I Built

  • Support inbox review queue and Gmail OAuth sync
  • Knowledge upload for policies, FAQs, and product docs
  • Policy lookup workflow for draft replies
  • PII redaction, encrypted token storage, and audit logs
  • Human review before Gmail draft creation

Architecture

The backend uses FastAPI, PostgreSQL, pgvector, encrypted OAuth tokens, audit logging, and protected admin routes. The frontend focuses on a review queue, message detail screen, draft workspace, source review, and privacy state.

Result

The result is a realistic support tool: inbox sync, policy review, privacy handling, OAuth integration, audit records, and an approval step before draft creation.