First 60 does not save your answers.

What happens to your three answers

Your answers travel from your browser to our server and on to the model provider that produces the read. The server keeps them in memory only while the read is produced. It does not write them to a database, a log or a file.

The model provider is Anthropic. As checked on 20 September 2026, Anthropic says standard API inputs and outputs are deleted from its systems within 30 days. Exceptions can apply for Usage Policy enforcement, legal obligations, or a separate retention agreement. Anthropic says commercial API inputs and outputs are not used to train its models unless the customer opts in.

Provider details: Anthropic retention policy and model training policy.

What we do record

For each read: the request status, how long it took, the pattern name, the confidence level, whether the result passed our checks, and a random request id. Never the text you typed. Never the text you were shown.

Usage events, such as a result shown or a card downloaded, carry only short labels and numbers. Your free text never leaves the page in an analytics event. You can watch every event yourself by adding ?qa=1 to the address.

The card

The card is drawn and downloaded in your browser. It starts with a privacy-safe summary that does not include your answers, meeting details or feared impression. You can explicitly add the generated result text, then edit or remove any line before download.

What to leave out of your answers

Use roles, not names. Leave out private company facts, health details and anything else you would not say to a stranger. The read works from the shape of the meeting, not from identities.

No account, no email

The full result appears without signup. No email is asked for before, during or after the read. If that changes, this page changes first.