Travel & trips: AI agent use cases
Flights, hotels, weather windows and trip planning.
Travel is where agents promise the most and get blocked the most. These cases test flight prices, which booking sites let an agent in at all, weather windows, and planning trips end to end, with every site we touched and every block we hit.
Every card shows two ratings: whether we reproduced the result (V2 reproduced, V1 partly, F failed, V0 not yet run) and how much account access the task needs, from L0 (public web only) to L4 (spends money or deletes). How we test.
6 cases: 1 reproduced, 3 partly reproduced, 2 not yet run.
Which travel sites let an agent see fares?
Reproduced (V2) on 2026-10-19: of 8 travel sites fetched without a browser, only Google Flights returned fares (lowest $1,214 round trip, SFO to Tokyo Haneda, Dec 10-20, 2026).
Pick a trip window that avoids the rainy season
Partly reproduced (V1) on 2026-10-19: 5 seasons of Open-Meteo data show Phu Quoc and Ho Chi Minh City driest for Dec 15-Jan 5 (about 25 mm each) while Ubud stays wet (about 227 mm); flights and budget were not tested.
Price a Japan round trip (and why agents disagree)
Partly reproduced (V1) on 2026-10-19: Google Flights gave a lowest fare of $1,214 round trip for a stand-in SFO to Haneda itinerary; the two-agent price comparison in the claim could not be tested with Grok Bot alone.
Restaurants within walking distance of a Miami Beach hotel
Partly reproduced (V1) on 2026-10-19: OpenStreetMap listed 33 restaurants within 500 m of The Betsy South Beach, with distances and cuisines but no opening hours, ratings or prices.
'Organize me a trip based off today's e-mail'
Sourced only (V0), listed 2026-10-19: “'Organize me a trip based off today's e-mail'” is not yet verified by triedagents because it needs L1 access (reads private data).
Agent plans a work trip and buys the flight
Sourced only (V0), listed 2026-10-19: “Agent plans a work trip and buys the flight” is not yet verified by triedagents because it needs L4 access (spends money).
Search and filter all 19 cases → · How we test
Get one verified case every weekday
One agent use case we actually re-ran, every weekday. Free.
We only store your email address. Every issue has a one-click unsubscribe link. Privacy