User-triggered
cohere-ai is operated by Cohere. Fetches your page because a human asked an assistant to open it right now. Blocking it breaks a live request.
Cohere runs it as a user-triggered fetcher, which means it fetches one page at the moment a person asks an assistant to open it. There is no index and no schedule: somebody has pasted your link or asked for your site by name, and is waiting for the answer while the request happens.
What blocking it costs you: Cohere’s grounded generation, which sits behind a large number of enterprise assistants, cannot retrieve you in response to a prompt. A link somebody pasted into an assistant fails while they are watching. They asked for your page by name and got an error.
These are two different strings and confusing them is why a rule that looks right does nothing.
A robots.txt rule matches on the product token, case-insensitively, and
ignores the rest of the user-agent header entirely.
| robots.txt token | cohere-ai |
|---|---|
| Operator | Cohere |
| Category | User-triggered |
| Full user agent | Not published by Cohere. Match on the token above. |
Where an operator has not published the exact string, this page says so rather than inventing a plausible one. A user agent you can grep your logs for is worth nothing if it is a guess.
Paste this into robots.txt at the root of your domain.
User-agent: cohere-ai
Allow: /
Sitemap: https://axray.online/sitemap.xml
An empty Disallow: and Allow: / mean the same thing to a crawler. What does
not mean the same thing is having no rule at all: absence is permission by default, but it is
permission nobody wrote down, and it survives only until somebody adds a blanket
User-agent: * block without thinking about this crawler.
User-agent: cohere-ai
Disallow: /Before you paste that: cohere’s grounded generation, which sits behind a large number of enterprise assistants, cannot retrieve you in response to a prompt. That is the cost, and it is paid silently — no error appears in your logs, no report tells you, and the traffic you lose was traffic you never saw arrive.
Measured on 2026-09-06, by reading the robots.txt of
292 public websites and resolving each one against this crawler specifically.
| Verdict | Sites | Share |
|---|---|---|
| Blocked | 37 | 13% |
| Explicitly allowed | 201 | 69% |
| No rule either way | 54 | 18% |
No site is named, here or anywhere else on this domain. The count is the useful part; a league table of businesses that never asked to be measured is not.
The row worth reading twice is the last one. 54 of 292 sites have written no rule about
cohere-ai at all, which means their position on it is an accident rather than a decision — whatever
their User-agent: * block happens to say.
Reading your own robots.txt is not the same as knowing what a crawler concludes from it.
Precedence between a User-agent: * group and a named one, the longest-match rule between
overlapping paths, and a token you spelled slightly wrong all produce a file that looks correct and
behaves otherwise.
npx axray-cli your-site.comThe scan resolves your file against all 54 crawlers on this list individually and reports which ones are allowed, blocked, or covered by nothing. It is free, needs no account, and installs nothing.
cohere-ai is a user-triggered fetcher operated by Cohere: it fetches one page at the moment a person asks an assistant to open it. There is no index and no schedule: somebody has pasted your link or asked for your site by name, and is waiting for the answer while the request happens.
Only if you are willing to pay what it costs. Cohere’s grounded generation, which sits behind a large number of enterprise assistants, cannot retrieve you in response to a prompt. A link somebody pasted into an assistant fails while they are watching. They asked for your page by name and got an error.
Cohere does not publish a full user-agent string for this crawler. The robots.txt product token is cohere-ai, and that is what a rule matches on; matching is case-insensitive.
Scan your site with AXRAY. It resolves your robots.txt against 54 named AI crawlers individually rather than reporting one verdict for all of them, so it will tell you whether this specific crawler is allowed, blocked, or covered by no rule at all. It is free and needs no account.
ChatGPT-User — OpenAIClaude-User — AnthropicPerplexity-User — PerplexityMistralAI-User — MistralGoogle-NotebookLM — GoogleGoogleAgent-URLContext — Googlekagi-fetcher — Kagimeta-externalfetcher — MetaThe full reference: all 54 AI crawlers, and who blocks each one.
See which of these 54 crawlers your own site is blocking, and what each one costs you. One scan, no account.