Tripadvisor’s new AI review summaries are glossing over accounts of food poisoning, sexual harassment, and serious hygiene failures, a report by consumer watchdog Which? has found.

Travelers browsing Tripadvisor now see an AI summary at the top of a hotel’s page. While these summaries may look like a useful snapshot, guest reviews further down the page can tell a very different story.

Tripadvisor’s AI summary describes the five-star, all-inclusive Riu Palace Santa Maria in Cape Verde as “popular with many travelers,” with “spacious rooms,” “diverse restaurants” that earn “rave reviews,” and cleanliness described as “spotless.”

But recent guest reviews on Tripadvisor paint a far darker picture.

Guests at the Riu Palace reported “exceptionally poor hygiene,” “no basic cleaning or hygiene standards,” and food that was “awful, bland, unsafe and inedible.” One guest said she was served raw chicken.

Another shared photographs of flies and birds in the buffet food. Another said they spotted “dead little roasted mice by the sitting area” during their “nightmare” holiday.

One guest whose whole family fell ill wrote: “This place will destroy holidays, and [has the] potential to take lives.”

When Which? checked in March, it found 102 mentions of food poisoning at the Riu Palace. The resort also had 32 one- and two-star reviews posted between December 2025 and April 2026 alone, 14 of which said at least one member of the party fell seriously ill with some form of food poisoning.

Travel planning bot failures

Another Tripadvisor AI tool, an interactive trip-planning bot called Ollie, also failed to warn travelers about poor hygiene.

When asked directly about the risk of contracting food poisoning at the Riu Palace, Ollie said food poisoning was “quite unlikely” and that the resort had a “strong reputation for high hygiene standards.”

Which? investigation on Tripadvisor's AI summaries and new bot Ollie

When Which? asked Tripadvisor about its AI summaries, the company said it prioritizes “transparency and impartiality” and that its summaries “surface a range of both positive and negative community feedback associated with listings.”

Tripadvisor also told Which? that Ollie “draws from a selection of reviews based on detail and recency, and matches by language and context,” but added that it is a “product in development” and that it is now actively looking into several examples provided by the consumer group where reviews did not match.

The Riu Palace was not the only hotel where Which? found serious complaints missing from Tripadvisor’s AI summary.

Similar reports at the Garza Blanca resort in Cancun and the Occidental Caribe in the Dominican Republic were also glossed over by AI summaries that praised “immaculate cleanliness” or made only a vague nod to “inconsistent” cleanliness and “maintenance issues.”

Accounts of harassment downplayed

Tripadvisor’s AI summaries also appeared to downplay reports of sexual harassment, according to Which?

At Kaia Coracesium on Turkey’s Antalya coast, several reviewers who visited last summer said they felt unsafe because of repeated sexual harassment from male hotel staff, including inappropriate jokes and gestures and repeated requests to connect on social media.

Two different guests reported that a male staff member followed their daughters to ask for their social media details. In one case, the reviewer said a restaurant worker followed her up the stairs to her room.

Tripadvisor’s AI review summary described the service as “friendly.” The closest it came to acknowledging these allegations was: “Lapses [in service] noted by a few.”

Comparison with Google’s review app

Which? also compared Tripadvisor’s AI summaries with Google’s. For the Riu Palace, Google warned of “potential for illness” and flagged “outbreaks of illness” and “concerns over birds in the buffet areas.”

For the Britannia International hotel in London, Google said it was “frequently rated as one of the worst hotel chains in the UK” and highlighted reviews describing “filthy” conditions and “horrendous” service.

Tripadvisor’s summary of the same hotel said guests “often praise the clean rooms” and described the atmosphere as “charming.”

According to Rory Boland, editor of Which? Travel, while Tripadvisor may insist users can still fact-check its summaries against real reviews, it ignored the fact that it made the decision to push these summaries to the very top of the page.

“The platform has a responsibility to revisit the accuracy of its AI summaries and AI chatbot."

Rory Boland, editor of Which?

“In the meantime, users should scroll past these summaries and look at guest reviews, particularly one-star ratings, and at reviews on other sites, to make sure their next stay is a safe one.”

AI summaries are still a work in progress. A new study found that Google’s AI Overviews feature provides accurate, reputable responses roughly 91% of the time, which actually means that tens of millions of answers churned out every hour are erroneous or at least questionable.