Travel Disruption Orchestration

Overview

When travel is disrupted, operators must reconcile passenger context, fare rules, and rebooking options quickly — manual handling is slow and inconsistent, and a purely generative AI approach cannot be audited. I built JourneyMind at the Amadeus + Contentstack AI Hackathon to test whether AI can prepare context while a deterministic decision engine produces recommendations operators can explain and defend. React/TypeScript and FastAPI, with Playwright-tested operator flows.

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

I built JourneyMind during the Amadeus + Contentstack AI Hackathon as a proof of work for an operational workflow: AI orchestration plus a deterministic decision layer that produces actionable recommendations.

Who benefits

Operations agents and travel advisors who need to act quickly and consistently during disruptions — with a recommendation they can understand and stand behind.

Current status

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

Architecture

Technology stack

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

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

Future direction

• Production hardening: auth, rate limiting, observability, resilience
• Live data integration for disruptions, fares, and rebookings
• Configurable constraints without code changes
• Audit log for recommendations and manual overrides