What each week held
Withheld: something was read in 1 week of the last 12. A series needs at least 2 to say anything a single reading does not.
What it declares
The reading listed none. That is what the reading listed, not a statement that this product carries nothing.
What users raised
- wrong/outdated opening hours
- venues permanently closed or hallucinated
- outdated transit/ferry/visa info
- over-optimistic pacing/timing
- backtracking/illogical routing
- generic recommendations ignoring traveler needs
Themes people raised in public. A complaint is somebody’s opinion, not a measurement of the product.
Everything on record
5 observed claims. Newest first; the tag on each row is what kind of claim you are reading.
- PRODUCTCOMPANY CLAIMSep 30, 2026
Plot markets itself as a layer that catches these errors: it turns the plan into a real itinerary and, unlike the chat, works from trusted sources, verifying everything the AI saves so the mistakes a chat would make get caught before they cost a morning.
Another vendor explicitly building a product around solving the complaint theme.
www.plot.travel/blog/ai-travel-itinerary - POSITIONINGCOMPANY CLAIMSep 30, 2026
Vendors are now positioning dedicated tools against this exact complaint: GuruWalk markets that a travel-specific planner such as GuruWalk's queries a live activity catalogue, so what it proposes exists and can be booked on your dates, contrasting itself with general assistants that answer from training data and can state an opening time that changed.
Signals market response/product positioning built directly on the 'AI trip plans don't hold up' complaint, relevant for anyone tracking how vendors differentiate against generic LLM itinerary generation.
www.guruwalk.com/ai - DISCOURSEFACTSep 30, 2026
A separate study cited found that 90% of ChatGPT itineraries contain at least one error, including closed restaurants, wrong opening hours, and fictional places, with 52% suggesting visits outside opening hours and 24% recommending permanently closed venues.
A second independent data source corroborating the same failure pattern, reinforcing it as a mainstream (not niche) critique of general-purpose LLMs used for travel planning.
tripprof.com/en/blog/why-ai-cant-plan-your-trip/ - DISCOURSEFACTSep 30, 2026
A quantitative study of 356 AI-generated itineraries covering 2,735 planned days found that across 356 AI-generated itineraries covering 2,735 planned days, 43% of days carried at least one verifiable fault: a venue shut at the scheduled hour, a visit running past closing time, a day that backtracks across the map, or the same place booked twice, with venue-closed-at-that-hour errors alone affecting 22.7% of days.
Gives the complaint theme a measured baseline rate rather than anecdote, strengthening the case that this is a systemic, third-plus-sighted issue crossing into mainstream travel-tech discourse.
monkeyeatingmango.com/research/ai-itinerary-errors-data-study/ - COMPLAINTUSER OPINIONSep 30, 2026
A widely repeated complaint theme is that AI itineraries get basic facts wrong: assistants can suggest restaurants that have closed, get opening hours wrong, or send travelers to attractions on days they're closed.
Affects any traveler relying on raw LLM output (ChatGPT, Claude, Gemini) for logistics without verification.
www.plot.travel/blog/ai-travel-itinerary
A record of what Forge read in public about AI trip plans that do not hold up — its own pages and what people wrote about it. Nothing here is a test of the product, a ranking or a score, and Forge has no relationship with this company.