Problem & Challenge
Traditional travel agencies in South Asia operate through highly fragmented communication channels: customer discovery occurs through manual WhatsApp chats, tour pricing relies on unstructured spreadsheets, and package curation requires days of back-and-forth consultation with airline and hotel supplier portals.
FlightOne was conceptualized as an AI Travel Operating System (AI-TOS) designed to automate this lifecycle. The platform needed to fulfill two critical mandates simultaneously: deliver a cinematic, high-conversion commercial web agency that showcases bespoke international tours (Maldives, Dubai, Turkey, Thailand), while providing a dedicated conversational AI consultant (Ava) capable of real-time flight search, hotel tier pricing (3★, 4★, 5★), and booking orchestration.
Technical Approach & Architecture
FlightOne is engineered as three tightly decoupled yet unified systems:
- Commercial Web Agency: A high-performance Next.js web application built with responsive SCSS modules, Lenis smooth scrolling, and dynamic destination visualizers.
- Conversational Assistant Client: A lightweight React application where travelers converse with Ava, explore structured recommendations, refine dates, and review flight fares.
- Modular API Server: An Express.js backend using Prisma ORM on PostgreSQL that enforces deterministic pricing rules, manages itinerary drafts, handles token authentication, and coordinates GDS fare audits.
Engineering Challenges & Solutions
1. Deterministic Pricing vs. Generative LLM Variance
Large language models are inherently probabilistic, making them prone to hallucinations when calculating flight fares, currency conversions, and seasonal surcharges. Allowing an LLM to invent pricing would result in severe financial discrepancies.
Solution: We separated semantic understanding from business calculations. Ava handles natural language intent extraction and structures parameters into typed JSON payloads. The Express/Prisma server evaluates live fare metadata, applies tiered markup formulas, and returns verified pricing tables to the client, guaranteeing zero pricing hallucinations.
2. Cross-Device Consultation Continuity
Travelers frequently initiate trip consultations on mobile devices but complete itinerary reviews on desktop computers. Maintaining active session state without requiring mandatory upfront registration was essential for user retention.
Solution: Implemented guest UUID tokens stored in encrypted client cookies that bind conversation threads to ephemeral PostgreSQL session records. When travelers choose to register or authenticate via JWT, the server merges the guest consultation history into their permanent profile seamlessly.
Key Features & Capabilities
- Bespoke 24-Hour Itinerary Pipeline: Automated day-by-day travel plan generation tailored to honeymooners, families, and corporate groups.
- 3-Tier Accommodation Benchmarks: Instant comparison matrices between 3-star budget, 4-star boutique, and 5-star luxury options.
- Multi-Repo Architecture: Clean domain isolation across agency storefront, client chat UI, and server backend.
- Human Escalation Fail-Safe: Seamless handoff from AI consultant to human travel agents for visa-sensitive approvals.