Golfers describe a trip in their own words and get resorts ranked on what similar groups actually booked, with the reasons shown.
Your Golf Travel AI Trip Advisor
AI Exchange Hackathon
easyJet holidays Hotel and Points of Interest Map
City-break shoppers see every hotel on a map next to the points of interest they care about, with walking routes and what guests say.
A map-first hotel search that places every hotel against nearby points of interest, routes, and guest reviews, from a plain-language request. Built at the MACH AI Exchange, where MACH Alliance members work on a brand's live business problem.
What the agent does
Turns a plain-language request into search filters, maps matching hotels against nearby points of interest and routes, and summarizes what guests say.
- Brand
- easyJet holidays
- Built by
- The easyJet holidays team with Foster Made, Algolia, and Amplitude
- Contributed by
- MACH Alliance (Hub operator)
- Industry
- Travel & Leisure
- Audience
- B2C
01
The problem
Why this exists
For a city break, location is the product. Shoppers want to know whether a hotel is near the event, the landmark or the old town, and how long it takes to get there. easyJet holidays sells 11,000 hotels across 189 destinations, and a list of hotel names can't answer that question.
Read more
The second question is what other guests thought. That feedback exists across surveys, reviews, and site behavior, but it is scattered, so it rarely reaches the next shopper. A customer can visit up to 11 times before booking.
02
Outcomes
What this demonstrates
- Hotels appear on one map alongside nearby points of interest, with walking routes, transfer times, and the local forecast.
- Shoppers search in plain language. The request becomes filters, with a rules-based fallback if the AI is unavailable.
- Guest reviews are turned into themes and sentiment, and anything the AI is unsure about goes to a person.
Read more
- Reviews sit in the same data model as bookings and site visits, so one source answers questions across all three.
- Built on representative mock data, so partners could work without touching customer records.
What you would add to ship it
- Real customer and review data in place of the representative mocks used for the proof of concept.
- Coverage beyond the three destinations with live data.
- A booking path from the map. Prices shown are illustrative and no booking is submitted.
03
How it works
Architecture
Reviews, satisfaction surveys, and third-party feedback flow into one analytics model alongside website and booking activity, linked by customer and hotel. Review text is enriched with themes and sentiment on the way in, and anything below a confidence threshold goes to a person.
Read more
Cloud functions combine that with easyJet holidays' hotel, destination, and booking feeds, and with open map data for points of interest, routes, and weather. Two search indexes, one for places and one for hotels, power the map.
On the shopper's side, a language model reads the request and summarizes the results, with a rules-based fallback. The same enriched data also feeds dashboards, a chatbot, and agents for internal teams.
Tech stack
Amplitude AI FeedbackAmplitude Export APIAlgoliaGoogle Cloud RunVercelOpenStreetMapMedalliaGA4
Everyone credited on this solution
Resources
Next step
Request an intro
This one is the MACH Alliance’s own work. Ask about making hotel location and reviews legible, and the people who built it will answer.
Not ready to talk to anyone? MACH Insider is the Alliance mailing list. New solutions, program openings, and the research behind them, once a month.
Related solutions
Product recommendations arrive with a reason a shopper can read, not only a score.
IPSY Customer Preference Knowledge Graph
AI Exchange HackathonShoppers see relevant products from sister brands without being redirected off the site they are on.
Athena AI Cross-Brand Recommender
AI Exchange Hackathon
Verification
Contributor submission
The detail on this page comes from the contributor's own account of their own work. The MACH Alliance reviews a submission before publishing it and does not independently verify the figures in it.
What this page does not establish
- No engagement, speed-to-booking or conversion result has been published.
- The review enrichment ran on mocked data, so its accuracy on real easyJet holidays reviews is not shown.
Where this came from
Written from the easyJet holidays session deck at MACH X Amsterdam, September 29–30, 2026, and the demo repository README, which is private. The proof of concept ran on mocked data with representative structures.
Status: Reference prototypeAdded Oct 15, 2026A listing is an editorial decision, not a MACH Alliance certification.
Built something worth showing?
Put your agentic solution in front of the enterprise leaders who use the hub to decide what to build next. Submissions are open to MACH Alliance Members, Collaborators, or Ambassadors.