llms.txt has become a fixture in GEO guides and AI-visibility checklists.
The recommendation shows up in nearly every list and every guide: add an llms.txt file so AI engines see you and cite you. By now it sounds like something you must have.
So before you add it, it’s worth asking whether the file actually does what it promises. The real picture looks nothing like what’s being sold to you.
Bottom line
You don’t need an llms.txt file.
Not for Google, and, based on what I actually see in the logs, not for the AI engines either. Not right now.
Maybe one day it’ll serve AI agents. That’s a different story, and I’ll get to it. But before I start nitpicking, let’s get straight on what llms.txt even claims to do.
Wait, what is llms.txt?
It’s a proposal. Not a standard.
Jeremy Howard published it in September 2024: a Markdown file at the root of your site that hands an LLM a clean summary of your content, so it doesn’t have to parse full HTML buried in ads and JavaScript.
The original idea was mostly for documentation and development environments. Places where a model needs quick access to docs and APIs. Not for ranking, and not for showing up in answers.
Why does everyone recommend llms.txt?
In May 2026 Chrome promoted its Agentic Browsing category in Lighthouse from experimental to default. Since then, anyone running a normal Lighthouse report automatically gets a check for whether an llms.txt file exists, and a lot of people saw the red “missing file” flag and assumed it was an SEO requirement.
But look where Chrome filed that check: under Agentic Browsing. Not under SEO.
What’s the difference between agentic and GEO?
There are two completely different things being mixed up here. Agentic AI is agents taking actions: AI browsers, the Claude Chrome extension, and bots that navigate a site and do things on it.
GEO, AI visibility, is something else: getting your brand shown and cited in the answers of ChatGPT, Gemini and Perplexity.
llms.txt, if anything, belongs to the first world. To an agent that needs a clean map of the site to operate on it. There’s no proof it does anything for the second one, the one that decides whether you get cited.
Does Google use llms.txt?
The answer, at least from Google, is no. Google added an explicit section to its official docs: you don’t need to create new files to appear in Google Search, because Google Search doesn’t use them. It also calls the AEO/GEO “hacks” things that aren’t really effective.
Sounds settled. Except I don’t take everything Google’s team says at face value.
Google speaks from the perspective of Google Search, and it scopes things narrowly. “Search doesn’t use llms.txt” is a fact about Google Search only. It says nothing about ChatGPT, Claude or Perplexity.
So I didn’t settle for the statement. I went to the logs.
What do the logs say about llms.txt?
At Wix I managed the team that built llms.txt support, at the scale of hundreds of millions of sites, and we tracked what shows up in the logs. Actual usage: zero.
I also have access to logs from some of the largest sites in Israel, and there I can put a number on it: requests for llms.txt don’t even amount to 0.0001 of all requests. And what little does come in, comes from unknown, obscure players. Not from the major crawlers that feed the answers in ChatGPT and Gemini.
The bots that actually matter for GEO don’t bother fetching this file.
When do you actually need llms.txt?
There’s an edge case that does make sense: AI agents navigating your site. A file that hands them a quick map can save them crawling time. Chrome notes this too, and also notes that the file is optional and that the audit is marked N/A if it doesn’t exist. But even that use isn’t here yet.
And that’s exactly what happens when I run Lighthouse on my own site: I have no llms.txt, the check sits right next to the WebMCP checks under Agentic Browsing, marked Not Applicable, and the category still gets a perfect score.
It’s prep work for an air conditioner you haven’t bought. You cut a hole in the wall for a unit that may or may not arrive. Maybe you’ll need it. Maybe not. In the meantime there’s a hole in your wall.
In the very, very best case, llms.txt is a nice to have. Nothing more.
What should you do for AI visibility instead?
Instead of investing in a file the bots don’t read, focus on what actually moves the needle:
- Make sure the information about your brand and product is correct and consistent everywhere AI engines learn from.
- Make sure AI bots can crawl your site without friction.
- Build content that answers real questions, in text that lives in the visible HTML. Because that’s what the engines actually read.
A few months ago I sat down with a good friend from the field and we talked about exactly this. After I laid out that there’s currently no proof the file works, not even a little, he said something I agree with: if it’s easy for me, one toggle in WordPress or a CMS, why not flip it anyway?
And he’s right. If it’s a two-minute toggle, there’s not much reason to resist. It can’t hurt, and it also shows the people above you that you’re doing something on the AI front. The problem only starts when you prioritize it over development and improvements already waiting in the queue, or when someone charges you for it like a GEO service.
The takeaway
If someone’s selling you llms.txt as an AI must-have, they’re selling you an AC installation for a wall with no AC. That may change as the agentic world matures, but until then the file simply isn’t needed.
Real AI visibility doesn’t start from a text file. It starts from solid technical SEO and a consistent entity that engines like ChatGPT, Gemini and Perplexity recognize and trust. That’s exactly where technical SEO meets GEO.
