AI drafts and suggests fixes. You approve.
For teams that want help writing and repairing tests without handing control to a model. AI drafts and explains. A person decides what changes.
How it works
- You work as usual. Record a test, run it, and open the failures.
- AI proposes. It suggests extra checks after a recording, explains why a run failed, or suggests a new selector for a step that stopped matching.
- You decide. Promote a suggestion or dismiss it. Nothing is saved until you save it.
- The allowance is visible. Each plan has a monthly AI allowance. When it is used up, tests keep running and AI waits for the next month or an upgrade.
What is included
- Suggested checks. After you record, AI proposes extra checks based on the page text the recorder saw.
- Why did this fail? A short, plain explanation of a failed run: the likely cause, what probably changed and what to try.
- Selector fixes. When a step’s selector stops matching, AI can suggest a new one. You promote it or dismiss it.
- Describe a test. Type what a test should do and edit the draft. AI can also suggest accessibility fixes, and point out pages your tests never visit.
- You stay in charge. AI does not change your tests by itself. A person promotes or dismisses each fix.
- What goes to Anthropic. Only minimised extracts, such as step labels, page paths, titles and short text snippets. Never screenshots, videos, traces, secrets, password values, cookies or test emails. Under our terms with Anthropic, it may not use them to train its models.
Plans. Every plan includes an AI allowance; higher plans include more.
Good to know
AI can be wrong. A failure explanation sees a small summary of the run, not the page, so treat it as a hint. Typed field values are sent for suggested checks only if an organization admin turns that on. It is off by default. We have not arranged zero data retention with Anthropic.
Questions
Can the AI change my tests by itself?
No. The AI proposes, for example a selector fix, and a person promotes or dismisses it. Agents connected through MCP also need a person’s approval for changes.
What data goes to Anthropic?
Only minimised extracts, such as step labels, page paths, titles and short text snippets. Never screenshots, videos, traces, secrets, password values, cookies or test emails. The privacy policy lists what each feature sends.
Is my data used to train AI models?
Under our commercial terms with Anthropic, it may not use the data we send to train its models. We have not arranged zero data retention.
Which plans include AI?
Every plan includes an AI allowance; higher plans include more. The counts on the pricing page are estimates, not guaranteed quotas.
What happens when the AI allowance runs out?
Your tests keep running. AI suggestions wait until the allowance resets next month or you upgrade.
Keep reading
Check your site the way a person would
Record your first test by using your site.
Accounts are opened on request for now. Contact us and we will set one up.