Manus tests on hotel booking engines
Manus.ai was prompted to book a September stay at hotels on 11 popular booking engines to test its navigation.
Manus succeeded on 8 of 11 booking engines, three of those with delays, and failed on D Edge, Simple Booking and Travelanium.
Overview
How it was set up
Manus.ai, built on Anthropic's Claude and Alibaba's Qwen models, got the same one-line booking prompt for each hotel on each booking engine.
Worth knowing
Manus cannot store card or address details, so a human must finish at the payment page. Success meant reaching it.
A prompt to start from
Please book me a room at [hotel name] from [check-in date] to [check-out date].
Written by Agentic Feats from the source. Not the author's exact prompt.
Sources 1
History
- Source published
- 2025-07-09
- Added to Agentic Feats
- 2026-10-13
- Pick
- No
- Markdown copy
- /c/manus-tests-on-hotel-booking-engines.md
More in research
36 featsResultIt created the text file as asked, but after clicking a result it took a screenshot too early and hallucinated the answer.
ResultOperator handled tour search and lesson plan but was slow; adding three grocery items took 15 minutes and an Uber price check took five.
ResultThe draft was usable but weaker than accepted NSF summaries; thinking mode helped, though it began hallucinating and misreading the sources.