Where does the llms.txt file go?
At the root of your domain, so it is reachable at yoursite.com/llms.txt. It goes next to robots.txt rather than inside a folder.
llms.txt Generator
The file an answer engine reads before it reads your site. It says which pages carry the answers, in your words rather than in a crawler guess.
Name your site, write the one line you want quoted back, list the pages that answer real questions, and take the file away.
Everything here is worked out in your browser. Nothing you type is sent anywhere, and there is no account to make.
This is the sentence most likely to be quoted back. Write it, do not leave it to be inferred.
Key pages
Optional pages
Optional is a reserved heading in the specification: it marks links a reader may skip when it needs a shorter context. Background and archive pages belong here.
Result
Fill in the fields on the left. Nothing is generated until you do, and nothing is filled in on your behalf.
How the number is worked out
- llms.txt is a proposal, not a standard every engine honours yet. It sits next to your sitemap and your robots file rather than replacing either.
- The value is in the notes. A list of URLs repeats your sitemap; a line saying what each page answers is the part a model can use.
- The title is the only part the specification actually requires. Everything else here is there because leaving it out gives away a sentence someone else will write for you.
What comes out
You will see
- A complete llms.txt file in the format the proposal defines
- Your summary as a blockquote, which is the line most likely to be quoted
- Key pages as a linked list, each with a note saying what it answers
- An Optional section, which is the reserved heading for pages a reader may skip
- A copy button and a download that saves it under the right filename
- A note on where the file goes and what it does not replace
How to use it
Three steps, and the third one is the point
-
Name the site and write one sentence
The sentence matters more than the list. It is the description a model is most likely to repeat, and if you do not write it, something else writes it for you.
-
List the pages that answer questions
Not your whole sitemap. The pages that settle something: sizing, shipping, returns, how the product is made, who it is for.
-
Add a note to every link
A list of URLs repeats your sitemap. A line saying what each page answers is the part that is worth reading.
What llms.txt is
llms.txt is a plain markdown file that sits at the root of a domain, next to robots.txt, and describes the site to a language model in the site owner words. It has a defined shape: a heading with the name, a blockquote summary, then sections of links where each link carries a short note.
It is a proposal rather than a standard every engine honours. That is the accurate position and it is worth stating plainly, because plenty of pages about this file imply an adoption that has not been confirmed.
What it costs to publish is ten minutes. What it changes, if an engine does read it, is which sentence describes you and which pages get reached for first.
Where the value sits, and it is not the links
A generator that turns your sitemap into a list of URLs has done nothing: the sitemap already exists and a crawler already has it. The part a model can use is the note next to each link, because it says what the page settles.
Compare a bare link to a sizing page with a link that says it explains how to pick a size without measuring. The second one can be matched to a question. The first one has to be opened and guessed at.
That is why the note field sits next to every row here rather than being optional, and why the summary line is asked for before anything else.
The tool
What this one does
-
Follows the format the proposal defines
H1 name, blockquote summary, section headings, and links written as markdown with a note after the colon.
-
Uses Optional as the reserved heading
Optional has a specific meaning in the specification: links a reader can skip when it needs a shorter context. Background and archive pages belong there.
-
Asks for the sentence, rather than inferring one
The summary is the line most likely to come back in an answer. Nothing here writes it for you.
-
Leaves out what you did not fill in
Empty rows do not appear. There is no filler text and no placeholder company description in the file you take away.
-
Downloads under the right name
The file saves as llms.txt, which is the only filename that works, and the tool says where on the domain it belongs.
-
States what it does not replace
It sits alongside your sitemap and your robots file. Neither of those stops mattering because this one exists.
Reading the result
What each line is telling you
- The H1 line
- Your site name. This is the only part the specification requires.
- The blockquote
- Your one sentence. Read it back and ask whether you would be happy seeing it quoted, because that is the job it is doing.
- Key pages
- The main section. Each row is a link and a note, and the note is the part that answers a question.
- Optional
- A reserved heading, not a general second section. Only use it for pages that can be dropped without losing the point.
A free tool answers one question.
A search audit answers the rest.
We look at your search visibility across Google and the answer engines, and tell you what is costing you orders. No charge for the first look.
In practice
What you can do with it
-
Publish it and see what changes
The file costs almost nothing to put up. Save it at the root of the domain and watch which pages get cited over the following months.
-
Write the sentence you want repeated
Most brand descriptions in an answer are assembled from whatever text was nearest. This is a chance to supply one on purpose.
-
Point at the pages that settle arguments
Sizing, returns, materials, compatibility. The pages a support inbox keeps answering are the pages a model keeps being asked about.
-
Keep it short on purpose
The value is in the selection. A file that lists everything has selected nothing, and reads exactly like the sitemap it duplicates.
Questions
llms.txt Generator questions
Do AI search engines read it?
It is a proposal, and adoption is not something we can confirm on your behalf. Treat it as cheap to publish and unproved in effect, rather than as a setting that switches something on.
Does it replace robots.txt or my sitemap?
Neither. Robots.txt controls access, the sitemap lists pages for crawling, and this file describes what the important pages answer. Publishing one does not let you drop the other two.
How many pages should I list?
Few enough that the selection means something. A dozen pages that settle real questions is more useful than two hundred that repeat the sitemap.
What goes in the Optional section?
Pages a reader can skip when it needs a shorter context: company history, archived posts, background material. It is a reserved heading with that specific meaning, not a place for a second list.
Is my data sent anywhere?
No. The file is built in your browser and never leaves it until you download it.
The rest of the set
Fifteen more, all free, all in the browser
- CPM Calculator Work out what a thousand impressions costs, or what a budget buys at a given CPM.
- CTR Calculator Clickthrough rate from clicks and impressions, or the impressions a target needs.
- Conversion Rate Calculator Conversion rate from visitors and conversions, with revenue per visitor beside it.
- ROAS Calculator Return on ad spend, the ACoS behind it, and whether your margin leaves any profit.
- CPC Calculator What one click costs, and what it costs by the time it becomes an order.
- CPA Calculator Cost per acquisition from media spend, and the ceiling your margin allows.
- CAC Calculator What winning a customer really costs, including the parts a platform cannot see.
- ARR Calculator Annual recurring revenue, with the net new figure that shows the direction.
- AOV Calculator Average order value, and what a target is worth against the same order count.
- Cost Per Lead Calculator What an enquiry costs, and what it costs once the unqualified half is priced in.
- LTV Calculator Work out what a customer is worth over time, so you know what you can pay to win one.
- Schema Markup Generator Generate the JSON-LD a product, article or FAQ page needs, ready to paste.
- Break-even ROAS Find the return on ad spend where a campaign stops costing you money.
- CRO ROI Calculator See what a conversion rate change is worth against the traffic you already have.
- Hreflang Generator Produce the hreflang tags a multi-country store needs, without the usual mistakes.
llms.txt is a file you publish, not a standard anyone is obliged to read. Serving it costs almost nothing, and whatever value it has sits in what it points at rather than in the file itself.
Where this comes up