Which websites have an llms.txt file?
On 29 October 2026, Minuttia and OpenAI's developer documentation both served public llms.txt files. They are two checked examples, not an adoption census. Our separate Minuttia agency record, read that day, has 3/8 Yes cells and a Machine readable Partial. That count concerns published agency evidence; it is not a score for the file's format or proof that an answer engine consumed it.
What we measured
Measured. Our agency scorecard counts published evidence, with only Yes contributing to the total. Partial and No remain separate statuses. The comparison is alphabetical, not a ranking. Broadcastwell is its publisher and is not scored.
| Agency | Method | Open data | Engines | Price | Refund | B2B cases | Reviews | Machine readable | Yes count |
|---|---|---|---|---|---|---|---|---|---|
| Minuttia | Partial | No | Yes | Partial | No | Yes | Yes | Partial | 3/8 |
The original company-site reads were on 15 September 2026. Reviews were read on 16 September 2026. Prices, refund terms and engine lists were rechecked on 28 October 2026. The saved source snapshot was read on 29 October 2026; the other cells retain their earlier field dates.
Reported. The Minuttia file and OpenAI developer file returned public content on 29 October 2026. This is an availability check, not an engine-use observation.
The publication count includes no new provider test and does not prove client results.
What this means for you
Reasoned. Read the file itself. Minuttia's saved file begins with a second-level heading identifying official company information. It describes the agency, its audience and selected proof. Its availability therefore does not establish that every example follows the proposal's requested first-level title format.
The OpenAI developer file starts with a first-level OpenAI Developers heading and routes readers to product documentation sets. Its API index is linked separately from that top-level file. This is a documentation map, rather than Minuttia's company-information document.
Minuttia's Machine readable Partial needs its actual criterion beside it. Our comparison asks whether a buyer's AI can read the results through an account, export or connector. A public company summary does different work from access to the underlying answer records. Do not convert its file's successful response into a Yes for that broader criterion.
For an agency checking examples before publishing a file, the two source addresses show different choices about scope: company information at Minuttia and documentation routing at OpenAI. Neither returned file gives this page evidence about whether ChatGPT used it in a particular search answer.
The Minuttia audit also retains an Open data No, whose criterion is publication with a DOI. A file containing company information is not an open research deposit merely because both can be read as text. Keep that status separate from the successful read of its llms.txt address.
Also asked as
Which websites have an llms.txt file?
Related
Next step
Use Free 10-question check (one engine) to inspect a defined set of buyer questions. No email is needed; runs are limited per network and per day, and by the site's daily allowance.
For one documented gap, Fix one answer, $490. Keep the question and source receipt with the requested change.
Our published agency-audit criteria.
Prepared by the Broadcastwell team.
Page owner: Rohan Iyer, AI Engineer. Corrections: hello@broadcastwell.com