Naming likelihood: How many answers are likely to name you on each question in the next pass? (Sample data, fictional company)
States, for each measured question, how many answers in the next pass are likely to name you, from the repeated passes so far, with the base it rests on. Its accuracy is unproven: every figure is saved so a later pass can be compared with it.
Sample data, fictional company. Kalvenor Systems is a fictional company. Every sample on these pages was written from its recorded fictional receipts; no model was run, and none of it is a result about a real company.
Kalvenor Systems, a fictional company. All sample analyses.
A modeled estimate, not a measurement. It is shown with its basis and checked against your next delivered measurement, with that check shown beside it once it exists.
What it reads
Up to 120 scored answers and the per-question figures from your latest delivered measurement.
Every item in a result quotes the receipt it relies on. You review each saved result before anyone relies on it.
Fictional sample. No model was run.
What a result holds, on the fictional Kalvenor sample
Kalvenor Systems is a fictional company. This analysis returns a modeled estimate, and a modeled estimate is never shown on a public page as a result, even for a fictional company. So this page lists what each item of a result holds, and the sample's figures stay inside the account.
A modeled estimate, not a measurement. It is shown with its basis and checked against your next delivered measurement, with that check shown beside it once it exists.
Each item holds
- Question
- Answers likely to name you
- Answers in the next pass
- Observed so far
- How it will be checked
Checked against your next delivered measurement once it exists.
In a client account
Available now in a client account. There this analysis reads the answers ChatGPT, Claude, Perplexity, Google AI Overviews and Google AI Mode gave in the client's latest delivered measurement, and every result is saved for the client's review with the date it ran and what it read. This page reads no account.
Returns, item by item: Question; Answers likely to name you; Answers in the next pass; Observed so far; How it will be checked. What each analysis reads and returns, in our documentation.