llms.txt is a plain-text file offering AI crawlers a structured summary of what your site contains and where to find it — a new, complementary convention to robots.txt and sitemaps, aimed specifically at how AI assistants discover and reference sites. We write and structure it from facts you provide about your own site; we don’t decide what claims about your business it should make.
llms.txt authoring & deployment
An llms.txt file structured from facts you provide — we don't invent claims about your business.
- Full backup taken before we start
- If we can’t fix it, you get your money back
- We never ask for your own password
What we need from you
- A clear, factual summary of what your site or business actually offers, in your own words or existing content
- Confirmation of the specific sections or content areas you want highlighted
- FTP or file access to publish the resulting file
This or something else?
| You want a properly structured, detailed llms.txt file authored and published | This fix covers it |
| You just want basic crawler access configured, not detailed content authoring | Crawler configuration – robots.txt, AI bots, llms.txt, the more basic version |
| You want to know what content strategy will get AI assistants to recommend your brand | Outside what this fix does — that’s a strategic marketing question, not a file format |
| You want structured data (schema) implemented, a related but different mechanism | The relevant schema-type implementation fix instead |
What we do
- Gather accurate, factual information about your site from you and your existing content
- Structure that information into the llms.txt format’s expected sections
- Write clear, direct summaries derived from what you’ve provided, not invented independently
- Publish the file at the correct location
- Verify it’s accessible and correctly formatted
- Review the final content with you before considering it finished
What is included
- A structured, properly formatted llms.txt file
- Content derived from information and existing material you provide
- Verified correct placement and accessibility
- A review with you before finalising
Not included
- Deciding what your business should claim or emphasise as a marketing strategy — this documents what you tell us is true, it doesn’t craft positioning
- Guaranteeing any specific AI assistant uses, indexes, or references the file
- Ongoing updates as your site’s content changes substantially, unless separately arranged
- Basic crawler permission configuration, if not already covered — a related, separate fix
Questions about this fix
Will having an llms.txt file get my business recommended by ChatGPT or similar assistants?
No — this gives AI crawlers a structured, accurate summary if and when they access your site; it doesn't influence or guarantee whether any specific assistant chooses to reference, recommend, or represent your business.
Can you write something more impressive than what's actually true about my business?
No — we write from what you confirm is accurate, since an llms.txt file making inflated or false claims is a genuine credibility risk if an AI system surfaces it, and isn't something we'll produce.
Is this a widely adopted standard yet, or still emerging?
It's a newer, emerging convention that some AI systems are beginning to use — worth having in place as good practice, though it's not yet as universally established as robots.txt or XML sitemaps.
How is this different from just having good content on my site already?
llms.txt offers a distilled, structured summary specifically aimed at how AI crawlers process sites, which can be more efficient for that purpose than expecting a crawler to piece together the same understanding from your full site content alone.
Do I need to update this file often?
Only when your site's actual content or offerings change substantially enough that the existing summary would be inaccurate — it's not something requiring frequent, routine updates otherwise.
Related fixes
If this is the second time this year
A bad update breaking the site is a symptom of updates not being tested first. Care plans run every update on a staging clone before it reaches your live site, which is the actual fix for this happening again.
Your access, your rules
Create a separate admin account for us and delete it when we are done. For anything else, we get in touch and agree a method — never a form field on this site, never by reply to an email.
We back up first, always
Before anything is touched we take a full backup and keep it for 30 days. If a fix goes wrong, we put the site back exactly as it was.
If it is not what you bought
If the problem turns out smaller than what you ordered, we refund the difference. If it is bigger, we stop and send a quote before doing any extra work.
If we cannot fix it
You get back what we received. Diagnosis is on us — you only pay when the problem is actually solved. The payment processor takes its fee before the money reaches us, so we never hold it and it is not ours to return. That is true here as everywhere else.
If it comes back
Reply within seven days of delivery and we put it back on the bench at no cost. The fix is not finished until it holds.
What we are responsible for
If something goes wrong with a fix, our responsibility is limited to what you paid for it. We take a full backup first so mistakes can be undone, and we tell you before doing anything outside what you bought.