Overview
Discovery API
Developers
Shopping Intelligence
Case studies
Travel intent infrastructure
Turn a sentence into a shortlist worth booking.
MyEscapePlan reads how travellers actually describe a trip, ranks the destinations, dates and trip lengths worth considering, then verifies the ones worth acting on against live provider inventory.
Across 12 internal benchmark scenarios, Flights and Accommodation remove 67.7% of the logical shopping space while retaining 67.5% Recall@10.
Natural-language intent
Discovery
Verification
TRAVEL DISCOVERY INFRASTRUCTURE
Discovery API
Turn an open-ended, natural-language travel request into a small, ranked and explainable set of candidates, with provider-backed verification available for the ones you choose.
Natural-language travel intent
Destination, date and duration ranking
Optional provider-backed verification
Available now
DESTINATION & MARKET SHOPPING INTELLIGENCE
Competitive Shopping Audit
Turn controlled travel shopping data into evidence about how a destination or travel product performs against realistic alternatives.
Structured travel shopping data
Where the destination wins and loses
Origin, budget, season and trip-length analysis
Coming soon
One request, end to end
One sentence in. A ranked, verified shortlist out.
Travellers and AI agents describe a trip the way they would say it out loud. MyEscapePlan resolves that intent into ranked candidates, then confirms the ones you choose with provider-backed data.
Traditional search
How a trip is described
A fixed set of fields, filled in and re-submitted until something fits.
What comes back
Pages of results to read, compare and narrow by hand.
What gets shopped
Broad searching across far more of the market than a traveller will ever consider.
What you learn
Queries and clicks, with no record of why one option won.
How competitiveness is tested
Historical analytics: what was searched and booked, read back after the fact.
MyEscapePlan
Discovery + Verified Search
Unlocked
How a trip is described
A sentence in the traveller's own words, understood as stated.
What comes back
A short ranked shortlist, each option carrying the reason it is there.
What gets shopped
Only the candidates worth confirming reach live inventory.
What you learn
Verified outcomes that inform the next plan.
How competitiveness is tested
Controlled traveller scenarios shopped against real alternatives — demand simulation rather than hindsight.
Shopping Intelligence · coming soon
Traveller intent
From London, 4 days next month, under £300pp, somewhere warm with direct flights.
Understood as
London
3–5 nights
£300pp
Direct only
Flexible dates
Ranked shortlist
1
AGP
Málaga
3–5 nights · flexible window
Verified
from £248pp
Example
Strong fit
2
ALC
Alicante
3–4 nights · flexible window
Strong fit
3
PMI
Palma
3–5 nights
Possible fit
Discovery · Available now
Discovery API
Natural-language intent in, ranked and explained candidates out. Synchronous planning that makes no live supplier calls.
POST /api/v1/business/discovery
Destinations, date windows and durations
Reasons and qualitative fit for your UX
Verification · Pilot workflow
Verified Search
Provider-backed checks on the candidates worth confirming, returning live price and availability for the shortlist you actually shop.
POST /api/v1/business/searches
Asynchronous and provider-backed
Scoped and provisioned separately from Discovery
An intent-driven decision layer
Understand the request. Rank the options. Verify the shortlist.
01
Understand intent
Resolve a natural-language request into origin, dates, duration, budget, party and the preferences a traveller actually stated.
02
Rank what is worth shopping
Reason across destinations, date windows, durations, budget and traveller constraints to prioritise the combinations most worth attention.
03
Verify what matters
Confirm price, availability and fit for chosen candidates through provider-backed Verified Search, rather than shopping the entire space.
Evidence loop
Every verified outcome improves the next shortlist.
Provider-backed outcomes and downstream feedback create structured evidence for refining intent understanding, candidate ranking and search strategy over time.
Independent industry evidence
Travel shopping already runs at volumes where the wrong request is expensive.
Look-to-book ratios put many shopping requests behind every booking, and agentic travel adds another source of iterative, automated search as AI travel agents explore and refine options on a traveller's behalf.
1,000–10,000+:1
OTA & metasearch look-to-book
IATA's 2019 scalability study measured shopping requests per booking for OTA and metasearch traffic, the highest-volume shopping channel it examined.
IATA NDC Scalability Study · 2019 ↗100–300:1
Airline-direct look-to-book
IATA's 2019 scalability study contrasted OTA and metasearch volumes with roughly 100–300 shopping requests per booking on airlines' own websites.
IATA NDC Scalability Study · 2019 ↗150+
Tool calls in long-horizon agentic travel
TRIP-Bench reports realistic long-horizon travel dialogues that can involve more than 150 tool calls across 18 travel tools.
TRIP-Bench · 2026 ↗Look-to-book is an industry shopping-to-booking ratio. It is not a claim that a single traveller request produces that many HTTP calls. TRIP-Bench separately reports 150+ tool calls in realistic long-horizon travel dialogues; those calls span travel tools and are not flight-supplier calls alone.
Measured with MyEscapePlan
A smaller shopping space that still holds the right options.
Canonical benchmark · Flights + Accommodation · 12 scenarios · September 2026
67.7%
Mean logical shopping-space reduction
Across the equally sized Flights and Accommodation tracks.
67.5%
Recall@10 retained
Mean across the equally sized Flights and Accommodation tracks.
67.8%
NDCG@10 ranking quality
Mean across the equally sized Flights and Accommodation tracks.
Case studies · Coming soon
Shopping Intelligence case studies are coming soon.
The public case-study library will launch with the Competitive Shopping Audit methodology and benchmark.
Available now
Start with a Discovery API pilot.
A 4–6 week pilot measures integration quality and recommendation quality on your own traffic, with provider-backed Verified Search available where a pilot needs it.
MyEscapePlan Travel Intelligence
Travel intent infrastructure: natural-language discovery, ranked shortlists and provider-backed verification, plus travel shopping data and market intelligence.
MYESCAPEPLAN LTD · Company no. 16395758 · Registered in United Kingdom
Discovery API is available now. Destination & Market Shopping Intelligence is coming soon.
Discovery benchmark figures, their formula and their limitations are published in full.
Read the benchmark methodology ↗
Shopping Intelligence case studies are a separate release, and will publish with the Competitive Shopping Audit benchmark.
Legal
Terms & conditions
Privacy
Cookies