Check a landing page with Claude: what a prompt does and what your audience adds

How to check a landing page with Claude alone

• Paste the copy into the chat: use the text of the page. The URL alone works only if your Claude can fetch web pages.
• Set the frame: who reads the page, where do visitors come from (search, ad, referral), and what should the next step be?
• Ask for obstacles: where does a reader stop? What would someone with no background knowledge not understand? Which objection goes unanswered?
• Ask for evidence: for every point, a quote of the passage on the page.
• Second check: ask the same question in a new chat and compare. Anything that shows up only once is a hint, not a finding.

A sample prompt to adapt: “Here is the copy of our landing page. It is aimed at [audience]. Visitors come via [search term or ad]. The next step is [demo, trial, inquiry]. Name the three passages where a reader from this audience is most likely to stop, each with a quote and the reason. Do not give scores.”

Where a prompt reaches its limits

• No evidence-based audience: Claude judges from general knowledge about buyers. What actually holds your buyers back shows up in reviews, forums and conversations, not in the prompt.
• Agreement: Language models tend to agree with their users. A study by Anthropic calls this “sycophancy” and finds it in several widely used assistants. So ask for problems rather than approval, and check whether the criticism still comes when you don’t ask for it.
• Estimating instead of measuring: contrast, tap targets on mobile and page length can be measured. For each such statement, check whether it was measured or estimated from text or an image.
• No comparison: rating one page on its own does not tell you whether a new version lands better. That takes two versions and the same readers.

What 99takes in Claude adds

First, your audience: 10 to 14 personas covering a wide range, backed by public customer voices, each with its source, wherever they exist. You set it up once for 15 credits, and then it’s there for every check. See audience research for how that works.

Analyzing a page has several parts. Structure and reading flow are measured (1 credit). How the page comes across on desktop and mobile costs up to 12 credits, plus 2 to 3 for redesign suggestions. Then come the copy, seen from the personas’ point of view, the comparison with competitors and a plan for what to change first. See what 99takes checks.

If you want a new version to compete with the current one, 99takes writes it. You see it before the test, and then the personas read both blind (buyer simulation).

The honest limit: this is a simulation before launch, not a market measurement. The hit rate shows how often the jury was right; we publish it once there are ten decidable results.

What it looks like in the chat

You write in Claude: “Analyze https://[your-page] with our audience.” Claude calls analyze_page for this. 99takes first shows the price of each part, free of charge, and starts only once you say yes. The result arrives in the same conversation: what the current page is costing you, where readers drop off and what to change first.

If you want to test a new version right away: “Run an A/B test for https://[your-page].” Then test_page walks you through scope, price and the new version before the personas read it. For more questions to copy, see example questions.

Connect 99takes to Claude

In claude.ai, you add 99takes as a connector; no key needed. In Claude Code, you run one command: claude mcp add --transport http 99takes https://api.99takes.com/functions/v1/mcp. Then test the connection with “Are you connected to 99takes? How many credits do I have?”. Every step is on the setup page.

Frequently asked questions