When I asked an AI chatbot about the entry requirements for crossing from Vietnam into Cambodia, it told me I could get a visa on arrival at the land border. I trusted that answer and did not verify it against the official rules. When I arrived at the remote Vietnam–Cambodia border crossing in May 2026, border officials would not issue the visa for my nationality — the chatbot's information was outdated and contradicted Cambodia's current entry protocols. I was stranded at the border, unable to proceed, and it cost me hours of waiting in 40°C heat, a USD $250 emergency documentation fee, and missed travel connections.
1 Answer
Expert: Victor Gimenez, Director of Customer Experience, iVisa The chatbot's visa advice was wrong, and it stranded a traveller at an international border. In May 2026, a solo traveller named Rita Santos was crossing from Vietnam into Cambodia when border officials refused to issue her a visa on arrival at the remote land crossing — even though a general-purpose AI chatbot had told her she could obtain one there. Santos, who is travelling solo with the aim of visiting every country in the world, said the mistake cost her a USD $250 emergency fee and hours of waiting in 40°C heat, and left her close to fainting with no support at the crossing. The chatbot's answer reflected outdated rules that did not apply to her nationality or to that specific point of entry. The case prompted iVisa, a visa and travel documentation service, to issue an advisory in late May 2026 warning travellers not to rely on general-purpose AI chatbots for visa guidance. iVisa argues visa research is poorly suited to large language models: immigration rules change quickly, vary by nationality and by point of entry (airport rules and land-border rules often differ), and frequently require case-specific interpretation. Chatbots also rely on historical training data rather than live immigration records, so a confident answer can simply be out of date. And unlike a specialist provider or an official source, a general-purpose AI tool offers no assistance after an error and does not compensate users for losses. "Wrong information at the wrong moment has a real cost," Santos said. "I wasn't just dealing with a logistical nightmare, I was in survival mode. You need a tool you can actually trust when you are at your most vulnerable." Victor Gimenez, Director of Customer Experience at iVisa, said travel documentation requires current information and direct verification: "Travel is about freedom, but that freedom rests on the foundation of accurate legal documentation. We don't guess; we verify." **Bottom line:** an unnamed general-purpose chatbot gave outdated, incorrect entry requirements for a specific nationality at a specific land crossing, and the traveller who relied on it was stranded at the Vietnam–Cambodia border in May 2026. Visa rules are jurisdiction-specific and change often — verify them against an official government immigration portal, an embassy or consulate, or the IATA Travel Centre close to departure, and treat any AI answer as a starting point only. Source: https://cmotech.asia/story/ivisa-warns-travellers-over-ai-visa-advice-after-border-snag
Your answer
Sign in to verify this AI response.
Don't trust us — or the AI. Ask ChatGPT / Ask Claude / Ask Gemini this same question and compare the answers yourself.
More from this topic
Asked to plan trips, AI chatbots sent travelers to places that do not exist. Among the 485 U.S. leisure travelers in the Greetwell AI Travel Survey 2026 who had used or tried AI for travel, 55% hit at least one recommendation that was inaccurate, unavailable, nonexistent, closed or otherwise wrong. Broken down: 27% got incorrect prices, hours or other details; 21% were pointed to something fully booked or unavailable; 17% got something simply wrong for what they asked; 16% were sent to a place, tour or activity that did not exist; and 10% were recommended a business that was permanently closed.
Asked to cancel only the outbound leg of a round-trip SkyMiles award between New York JFK and Los Angeles while keeping the return, Delta Concierge told the passenger in writing: "Your JFK to LAX flight has been canceled, and your LAX to JFK flight remains booked." Delta's own refund confirmation shows the opposite: all 32,400 miles were redeposited and the full $11.20 in taxes refunded, with both DL752 (JFK-LAX) and DL938 (LAX-JFK) listed as canceled - the receipt even displayed "Refund Number: null". The AI confirmed an itinerary state that Delta's ticketing system had already destroyed, and Delta Reservations then told the passenger the original award could not be restored and that a replacement one-way would cost nearly twice as many miles.
A passenger asked United Airlines' customer-service chatbot how long she had to use a $200 United travel credit before it expired. The chatbot answered that the money would stay available for years. A screenshot of the exchange shows the bot stating that her $200 TravelBank credit "stays active for 5 years from the date it's deposited." The passenger, Alison Gil, planned around that answer and held the credit for a larger trip. A few weeks later United emailed her to warn that the same $200 in TravelBank cash would expire on September 27, 2026 - roughly one year after it was deposited, not five. When she questioned the discrepancy, she says United told her: "sorry, the bot told you that, but it's one year and we can't change it." The airline later acknowledged to NBC 5 Responds that its "AI chatbot provided this customer with the wrong information for her situation," while noting the disclaimer customers are shown saying information "may not always be complete or relevant."