Hi, I'm Asad Azam.

Problem

When travel is disrupted, operators must reconcile passenger context, fare rules, and rebooking options quickly. Manual handling is slow and inconsistent; a purely generative AI approach is unaccountable and cannot be audited.

Why I built it

AI orchestration prepares context and options; a deterministic decision engine evaluates them against explicit constraints and returns a justified recommendation an operator can understand and stand behind.

Stack

React · TypeScript · Vite · Tailwind CSS · FastAPI · Python · REST APIs · Playwright

Architecture

React/TypeScript frontend with Vite and Tailwind; FastAPI/Python backend over REST. The decision engine is separated from the AI-assisted orchestration step to guarantee reproducibility and auditability.

Lessons learned

Determinism alone does not guarantee explainability — rationale must originate in the decision process · Keeping AI orchestration outside the final decision step preserves auditability · End-to-end tests of the operator flow reveal more than isolated unit tests · Explicit constraints are more valuable than implicit model flexibility in regulated contexts

Current status

Hackathon build with complete architecture and core flows — no live data integration or production hardening.

Current focus

Hackathon build with complete architecture and core flows; production hardening and live data integration to follow.