Why this page exists
Tripozi publishes accessibility and dietary guidance. Someone reads a page here to decide whether a city is navigable in a wheelchair, or whether a dish is safe with coeliac disease. Those are questions where being wrong has a cost, and where the reader is entitled to know who is answering.
My name has been on the privacy policy, terms and contact page since the site launched — the legal entity is Usługi Informatyczne Szymon Łysek. What was missing was the editorial half: the pages themselves never said who stood behind them. This page and the bylines fix that.
What I actually do here
I am not a travel expert, and this site does not need me to be one. It is not built on my opinions about destinations — it is built on other people's data, which I collect, check and publish. Concretely:
- The OpenStreetMap pipeline. Every venue on the accessibility and dietary pages comes from OSM contributors' tags, queried live, scored and published with the tag it came from. I wrote the extraction, the rate limiting and the fallback that keeps a failed lookup from being reported as “this city has none”.
- The visa matrix, by hand. The visa pages are not AI-generated. Every entry was entered against the destination country's own ministry or immigration authority, and each one carries that source link and the date it was last checked.
- The open dataset. The wheelchair-accessibility extract on /data is published under ODbL with the OSM attribution it requires, so anyone can check the pages against the data rather than taking my word for it.
- Everything else. The code, the servers, the deploys, the monitoring, and the mistakes.
Where AI sits, and where it does not
Itineraries and destination prose are generated by a language model. The accessibility venue lists, the dietary venue lists and the visa requirements are not — those come from OSM and from government sources. The methodology page sets out which layer is which.
What went wrong, and what I did about it
In August 2026 I read our own Copenhagen accessibility page the way an outside expert would, and found it recommending an accessibility symbol that does not exist — the word it named is simply the Danish adjective for “accessible”. So I audited the named things across both verticals properly.
Across 566 named entities I found 19 invented and 37 misnamed. A hospital with a street that does not exist. Taxi operators no register knows. A transit assistance service under the wrong name. A Hebrew phrase for asking about kosher supervision that actually said something else. An Estonian phrase about cross-contamination that asked about cumin instead.
The cause was mine, not the model's. My prompts told it never to invent numbers and never to fabricate an address, and said nothing at all about names — and a model reads that contrast as a statement about which categories tolerate invention. Worse, one prompt offered an invented app as an example of good practice, so the pattern it was shown was fabrication.
I took those sections down rather than patching the errors I happened to have found, because fixing only the ones I checked would have left the ones I did not. They come back per city, after that city is regenerated and re-audited — not before. The full record, including what the audit did not cover, is published with the site.
I am putting that on my own author page deliberately. It is the least flattering thing about this project and the most useful thing you can know about it: when the content here was wrong, it was removed rather than left up.
Corrections
If something here is wrong — a venue that has closed, an address that does not exist, a visa rule that has changed — please tell me. Send the URL and what is wrong to [email protected] and I will fix it and say so. Corrections that survive regeneration are recorded in the codebase rather than patched into a cache, because re-running the generator on a bad claim tends to produce the same claim in a more convincing form.