Support llms.txt files for Zendesk knowledge bases | The place for Zendesk users to come together and share
Skip to main content
M
Molly14
January 15, 2026
Under review

Support llms.txt files for Zendesk knowledge bases

Related products:Knowledge
  • January 15, 2026
  • 7 replies
  • 197 views

As users increasingly use AI Agents like ChatGPT or Claude to troubleshoot, Zendesk-hosted help centers have two accessibility problems:

  1. Direct fetch is blocked - when an agent tries to access a help center URL, Zendesk's Cloudflare configuration returns a 403. The agent never sees the content.
  2. Web search returns stale content - when agents fall back to web search, they get whatever was last indexed. If a topic recently changed in our knowledge base, the agent may end up returning inaccurate, out-of-date answers from the stale search cache.

Zendesk should introduce an admin setting to host a `/llms.txt` file at the root of the help center domain. Publishing an llms.txt file would give AI agents a structured index of help center content optimized for LLM consumption. 

Ideally, Zendesk would also consider allowing verified AI crawlers through Cloudflare for help center content, since this is public documentation intended to be found. At a minimum, it'd be nice if we could add instructions to the llms.txt for agents to direct them to an agent-accessible source of help content.

    7 replies

    Emily Reidy
    Emily ReidyProduct Manager
    Product Manager
    January 20, 2026
    Hi Molly! Thank you for taking the time to provide us with your feedback. This has been logged for our PM team to review. For others who may be interested in this feature request, please add your support by upvoting this post and/or adding your use case to the comments below. Thank you again!
     
      Lauren35
      Lauren35
      March 17, 2026

      I'm a bit shocked this isn't getting more attention. Upvote, upvote, upvote. It's just a single file with a huge impact, more and more users are getting their information from AI bots, and this context file is becoming critical for doc managers. Please unlock this as a feature or provide information for us to host the file in some way as a workaround. Thanks!

        J
        Jeff49
        June 3, 2026

        @Zendesk it seems like this has been in the pipeline for a while now. When can we expect an update?

          Jimmy11
          Jimmy11
          Newcomer
          July 7, 2026

          Our use case is that we are attempting to have Zendesk Crawl a separate Readme page to use as a knowledge source for our AI Agents and general help center search, where several pages are being blocked for ingestion due to javascript preventing reading of body tags.  Since crawling only allows an XML URL, It would be much easier if Zendesk allowed llm.txt specifically from this site, so we can ensure AI searches on our help center would pull in all content from the readme website.

           

          ​@Ilsa for awareness

            J
            jonsibley
            July 9, 2026

            +1 — we've hit this exact issue. We publish llms.txt and llms-full.txt at the root of our marketing domain already, and wanted to do the same for our Help Center subdomain, but there's no way to host a static file at the root — Guide's theme editor only gives us control over page templates, not root-level files.

            We also confirmed the Cloudflare fetch-blocking directly with Zendesk support (ticket #14668037) — no self-serve opt-out exists today, and AI/LLM crawlers get a 403 while Googlebot is allowlisted. An llms.txt admin setting would help, but it's worth noting it won't fully solve the problem on its own if those same crawlers still can't fetch the pages llms.txt points to.

              Shawna James
              Shawna JamesCommunity Manager
              Community Manager
              July 28, 2026
              Updated idea statusFeedback submitted→Under review
                Katarzyna Karpinska
                Katarzyna KarpinskaProduct Manager
                Product Manager
                July 31, 2026

                Thanks all for the insights. As you know, Cloudflare regularly makes security improvements that occasionally catch legitimate traffic.

                Generally for third-party tools, the best approach is to connect through the Help Center API rather than scrapping help center pages — that's the route designed for integrations, and it avoids most of the blocking and CAPTCHA issues. Just keep in mind the API has usage limits, so it's best not to hit it too aggressively.

                We also recommend these two articles that walk through some problem solving tactics when it comes to resolving blocked traffic issues:

                If you've tried that and still run into trouble, raise a ticket with Support and the team can help further.

                Terms & ConditionsAccessibility statement