Does ChatGPT find an answer on your website?
See which answers AI finds on your website and what is missing. Get specific suggestions to improve your copy.
Free · no sign-up · about 20 seconds
One check per day and device. Your website address is not stored.
Reading your pages …
The six questions put to your copy
Ready to paste
Built from your own material. Read it through and put your numbers in, then it can go on the page.
What was measured technically
Two questions, not one
Other tools stop at the signals. Signals tell you a model can reach your copy, not that it finds an answer there.
Visibility
Six measurements in the source code: crawlers, raw HTML, llms.txt, sitemap, structured data, title and description. First question, whether the door is open. A morning of file work, and the copy comes next.
Answerability
A language model reads your pages and answers six questions from them alone. No prior knowledge, no benefit of the doubt. This is the question whether anything stands behind the open door. It costs an afternoon of writing and decides whether you get quoted.
A website can invite every crawler and still say nothing worth quoting. That is why the two numbers stay apart.
The six questions, one by one
These are the questions a prospect brings to any vendor site. A model asks them on their behalf.
-
What do you offer? 20 points
- Why it counts
- The first question any prospect asks and the first one sites fail. “We support companies on their journey” is not an answer, because it fits every company.
- What works as an answer
- One sentence with a noun in it that someone could order. “We build wooden staircases for period buildings in Cologne” carries further than any phrasing with the word solution.
-
Who is it for? 20 points
- Why it counts
- A model has to decide whether to match you to a particular request. Without an audience it has nothing to go on, and it would rather name someone it is sure about.
- What works as an answer
- Name the group and narrow it down. “For tax practices with five to fifty staff” excludes people, and gets quoted precisely because of it.
-
What sets you apart? 20 points
- Why it counts
- The costliest gap. When three vendors say the same thing, the model names the one it knows something else about. The difference is the only reason it names you instead of them.
- What works as an answer
- Something that is not true of your competitor. A number, a method, a limit. “We do not take jobs under twenty square metres” is a difference, “high quality” is not.
-
What does it cost? 15 points
- Why it counts
- Missing from most sites, and it costs twice. The prospect leaves, and the model cannot answer a price question with you in it.
- What works as an answer
- Three forms commit you to nothing and still count: a from price, a range, or a worked example. “A kitchen with us usually lands between 12,000 and 20,000 euros” is an answer.
-
How do people reach you? 15 points
- Why it counts
- Sounds trivial and is often missing from the copy anyway. A form is not a way to make contact as far as a language model is concerned, because it cannot fill anything in and the address is written nowhere.
- What works as an answer
- Mail address and phone number as text on the page, not only inside the form and not only as an image. Plus one sentence on what happens next.
-
Where are you based? 10 points
- Why it counts
- A large share of all queries is local: “near me”, “in Hamburg”. With no place in the copy you drop out of every one of those answers, even where you could deliver.
- What works as an answer
- Place and catchment area in the running text, not only in the legal notice. Working nationwide? Write exactly that, and it is an answer too.
The six technical measurements
All of them on the publicly available source. None of them needs access to your website.
-
AI crawlers allowed
25 pointsYour robots.txt is checked for six names: GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot and Bytespider. Blocking is usually accidental, inherited from a boilerplate.
-
Content in the delivered HTML
25 pointsYour copy has to sit in the HTML the server sends. If the browser assembles it first, some models see an empty page. The check counts the words and looks for the telltale empty container.
-
llms.txt present
15 pointsA file that states in note form what your website is about. Young standard, ten minutes of work. We have a generator for it.
-
Sitemap reachable
10 pointsThe list of all your pages, either declared in robots.txt or sitting at the usual address. Without it a crawler finds only what is linked.
-
Structured data
15 pointsJSON-LD tells a machine unambiguously what is name, address, price and opening hours. The check names the types it found instead of merely counting them.
-
Title and description
10 pointsBoth get quoted in answers as the short version. The check looks at whether they exist and whether the length carries: title up to 65 characters, description from 80.
Reference
Answer engines, and where they fail
AEO stands for Answer Engine Optimization. The difference from a search engine is small and consequential: a search engine shows your page, an answer engine talks about it. What it says is decided by your text.
A model quotes what it can back up
Language models with web search cite sources. They pick paragraphs that answer a question completely, without needing the rest of the page. A paragraph starting with “as described above” never gets quoted, because it does not stand on its own.
The most expensive gap is the price
Of the six questions we ask, price fails most often. The reason is almost always on request. A model can do nothing with that and answers “no prices are given”, which a prospect reads as expensive. An entry price, a range or a worked example all fix it.
Hedging words cost points, not politeness
We flag wording such as bespoke, tailored and on request separately. They are not mistakes, they simply sit where a number could have stood. Wherever such a word appears, the information ends for a model.
Content that arrives via JavaScript often does not count
We measure the word count in the delivered HTML, so in what the server sends before any script runs. Some crawlers execute JavaScript, many do not, and none guarantees it. Below sixty words of raw text a page counts as an empty shell.
Six AI crawlers, and what sets them apart
We check robots.txt against GPTBot and OAI-SearchBot from OpenAI, ClaudeBot and anthropic-ai, PerplexityBot and Google-Extended. That last one only governs training for Gemini, not ordinary Google search. Blocking it costs you no ranking.
Structured data is a second opinion
An Organization block with address and contact gives a model the same detail again in unambiguous form. That is worth most where prose is ambiguous, such as opening hours and prices. Three types or more on one page score full marks.
FAQPage works when the question is real
An FAQ block helps because question and answer are already separated, which is exactly the shape a model quotes. It does not help when the questions are invented to place keywords. Take the five questions people actually ask you on the phone.
Two numbers, because two causes
We calculate visibility and answerability separately and deliberately never add them. A site can be technically flawless and mute in substance, and the reverse exists too. A single score would blend both cases into one middle number nobody can act on.
What we do not measure
We read text, not a browser. Loading time, contrast, keyboard operation and how the page behaves on a phone are outside this check. Those need a page that is actually rendered, and that is a different job with different tools.
Common questions
What is AEO anyway?
Answer Engine Optimization. Type a question into ChatGPT, Perplexity or Google's AI overview and you get an answer instead of ten blue links. That answer carries either your name or somebody else's. AEO is the work of making sure it is yours.
How is it different from SEO?
SEO gets your page into a list someone picks from. AEO lets a model build an answer out of your copy. The first rewards findability, the second clarity. Much of the technical work is the same, what is asked of the writing is not.
Why two scores and not one?
Because the causes have nothing to do with each other, and neither do the remedies. Visibility is repaired in an hour of file work, answerability costs an afternoon of writing. One averaged number would hide which of the two you are looking at.
How does the tool know what is missing on my site?
It reads up to six of your pages, preferring pricing, services and contact, and puts them to a language model under a strict instruction: use no prior knowledge. If the answer is not in the copy, it counts as unanswered, even where the model knows your company.
Are you judging my business?
No, only the website. The difference matters enough to us that it sits as a rule in the instruction to the model. “The offering is not recognisable on the page” is a finding about your copy. “The offering is weak” would be presumption.
What are the filler phrases you show?
Where an answer is missing, something almost always stands in its place anyway. The tool quotes those spots verbatim so you can find them again on your own site. Usually they are turns of phrase like “tailored solutions” or “fair terms” that fill a line without saying anything.
Can I just take the suggested copy?
Read it and adapt it. It is built from your own material and picks up your form of address, but a suggestion does not know your numbers. As a scaffold it saves you the start, as finished copy it will not do.
Do you store my address?
No. The address is used for the check and not stored afterwards. All that is counted is how often the check runs per day, so it does not get overloaded.
Why only one check per day?
Every check reads up to six pages and then asks a language model. That costs money, and the tool is free. One check a day is enough to look at a website seriously, and it keeps the abuse out.
What do I do with the result?
Three ways are open: fix it yourself using the SEO chapters of the documentation, take a template that already has the six answers laid out as sections, or have it done with the AI Website Service.
What the twelve checks measure and how to close every gap yourself: the answer engine optimization guide.
Other free tools
Each answers one question about your website, in under a minute, without an account.
Your next web project
Build on a strong foundation.
Website, design rules and seven skills in one package. Explore templates for your next project.
- Complete page structure
- Seven skills included
- German and English
All of this is already done in a template
48 finished industry websites, each with built-in knowledge and seven skills. Structure, copy, structured data and llms.txt are set before you change a single thing.
- A complete website with every subpage, fully written
- Seven skills to guide your AI tool
- The complete code as a ZIP, yours forever
One payment, everything included. We show this at most once.