// case study · 2023
A hotel booking platform, fed by Booking.com and AI extraction
An end-to-end booking platform with Booking.com inventory sync, deep filtering parity, and AI-powered reservation parsing for inbound supplier PDFs.
The brief
Direct Hotels needed a booking surface that competed on filtering depth with Booking.com itself, while also accepting reservations from a long tail of suppliers who send PDFs in a dozen languages. We led the rebuild — Booking integration, deep filters, and the AI pipeline that automated supplier intake.
What we built
- Booking.com static-data sync with periodic delta refreshes and a local cache so search stays snappy even when the upstream is slow.
- Filtering parity with Booking.com’s surface — price, geography, amenities, ratings — implemented as a structured query layer with shareable URLs.
- Inertia.js frontend for the engine of the user experience, keeping the SPA feel without giving up server-side rendering for SEO.
- AI-powered reservation parsing (the same pipeline that became its own portfolio entry) wired into supplier intake: PDF in, structured booking out.
- Operations dashboard with override tooling for support — refunds, force-cancels, supplier escalations.
Outcome
The booking team got a UI as deep as the OTAs they compete with, plus an automated pipeline for the messy supplier-PDF problem that previously took hours of manual entry per day.
// next step
Have a project like this?
Tell us about it. We respond within one working day with a written estimate or a calendar link.