Before launch, 99takes shows how personas from your audience take in a piece of copy or a landing page: which version they prefer, what holds them back and how the page comes across. The jury is curated and runs on Claude; we don't have a language model of our own. Below is what you get back, in places with an invented example.
A buying committee reads copy differently from a family comparing two plans. Every audience is one of three kinds: business buyers, consumers or politics. The jury reads in the role that fits.
For political copy it judges whether a message lands. It does not judge the position itself, and it takes no side.
You name the address of your page, and 99takes checks it in one go: how the copy lands with your audience, how structure and reading flow are built, how the page comes across on desktop and mobile, and which of your core claims competitors make the same way. On top of that, a specialist reviewer looks at the craft of the page.
At the end there is an action plan, most important first. If an action needs information only you have, such as a figure, Claude asks you for it instead of making something up.
This is the A/B test before launch. 99takes writes a challenger version, for the opening or the whole page. You see it before the test and can change it. Only then do the personas read your current page and the new version.
99takes names the price for each scope first. It does not replace an A/B test with real traffic. It shows which version is worth taking live.
Not every persona counts the same. You decide who your offer is made for, the core, and who only reads along, the edge. The verdict follows the core; the edge is shown next to it.
If a version only wins with people at the edge, you get a warning instead of a win. Otherwise you would ship copy that convinces the wrong people.
Verdict follows the core: new version wins 4 of 4.
At the edge: 1 of 2.
Some copy puts nobody off and is nobody's first choice. The scores look fine, yet the copy pulls no one in. In that case the result carries a note, so you don't mistake a pale text for a good one.
Note: everyone likes it a little, nobody's first choice.
Add your brand promise in one sentence. Each persona says whether the copy keeps it or drifts away, with a short reason. This does not go into the score. It is a second question next to the first: copy can win and still leave the brand behind.
Brand promise: 5 of 6 say "keeps it".
Add your page and the copy of two or three competitors. For each of your core claims, 99takes shows whether a competitor promises the same (taken), something similar (contested) or none of it (open). Every rating carries a verbatim quote with its source.
It also shows where an open claim sits on your page: in the hero or further down. A claim three competitors make the same way decides no shortlist, however well it is worded. It compares what the texts say, not how the market perceives the vendors.
Open: "fixed price per environment". Sits in section 8 of 11, belongs further up.
Taken: "publish without developers" (competitors A, B).
99takes also writes: versions that compete with your current copy. From the objections of a run, from the customer voices and research behind your audience or, without any draft, as a complete page from your positioning and the story your copy should tell (old way, new way). On request with a specific method, such as AIDA, benefit-led or headlines only.
99takes does not invent customer voices or results. A figure that appears in none of the material is marked for checking, and where proof is missing, the copy carries a placeholder. The versions are then tested like any other copy, and the jury does not know where they come from. If a version was written from the objections of this very jury, the result says a win there is expected and only the market decides.
Version 2 · Proof first: "Fixed price per location, term [PROOF: minimum term]. No setup project."
Whether copy convinces is one question. How the page comes across to your audience is the other. In the design check the personas see the whole page themselves, on desktop and on mobile. Each one says, from their own role, how the page comes across, what bothers them, what they miss and what they would change. Redesign suggestions come with it. You get the screenshots, so you can see which page was checked.
This is the personas’ impression, not a measured result. It stands apart from the verdict on the copy, and unlike there, there is no hit rate yet. If you want copy, structure and impression together, analyze the whole landing page.
Owner, trade business: "I only see the button for the first call after scrolling twice."
Two to four drafts of the first screen, as an address, HTML or an image: light or dark, tiles or rows, with or without a picture. The personas say what gets through to them, what they would click and what makes them hesitate. The result shows which draft they would click, or that it is too close to call.
With five drafts, not every one needs a full run. 99takes sorts out which one is worth it. This is a shortlist, not a measurement, and the result says so.
A CFO reads copy differently when choosing a vendor than when justifying a renewal. So every persona also reads the copy in the other personas’ situations; that is the default. You see where the copy carries least. If you want each persona only in its own situation, choose 1:1 and pay less.
Instead of testing a whole page at once, the build goes section by section, with one decision per section. The steps stay comparable with each other, even across several sessions. At the end, the finished page has to beat the old one.
Every run has a detail page with each persona's scores for both versions. A study becomes a report with its own link that you send to colleagues or your client; in Slack or LinkedIn the link shows a preview with the result. You can revoke a link at any time. From the Pro plan on, a report can be limited to invited readers.
Report which version won in the market. That builds a hit rate per jury, always with the number of results and a range. It is published only from ten decidable results on; until then it reads "not measured yet".
The rate comes only from reported market results and belongs to exactly the jury that judged.
You can stage a persona round with any language model. What is missing is what lets you rely on a result:
claude mcp add --transport http 99takes https://api.99takes.com/functions/v1/mcp