Work · Travel · 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.

  • Laravel
  • Vue.js
  • Inertia.js
  • Booking.com API
  • OpenAI

The job

3 on the team,
12 weeks.

Client
Direct
Sector
Travel
Year
2023
Role
Tech Lead

Brief and outcome

The brief

What was needed.

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.

The outcome

What came of it.

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.

What was built

Shipped

5 parts,
shipped.

From

A selection of projects shipped through Syntorium and our CTO's prior engagements.

  1. Booking.com static-data sync

    Periodic delta refreshes and a local cache so search stays snappy even when the upstream is slow.

  2. Filtering parity

    With Booking.com's surface — price, geography, amenities, ratings — implemented as a structured query layer with shareable URLs.

  3. Inertia.js frontend

    For the engine of the user experience, keeping the SPA feel without giving up server-side rendering for SEO.

  4. AI-powered reservation parsing

    The same pipeline that became its own portfolio entry, wired into supplier intake: PDF in, structured booking out.

  5. Operations dashboard

    Override tooling for support — refunds, force-cancels, supplier escalations.

More work

Start

Send a brief.

We reply within one working day with a written estimate or a call.

Open the brief form

No newsletters. Your details aren't shared.

Or say hello.

Sunday to Thursday, 09:00–18:00, GMT+4. Remote engineers cover the EU and the US asynchronously. We work in English, Arabic and Urdu.