AI visibility in Depra is the share of stored AI answers that name your brand: answers that name you, divided by all answers to your tracked questions in the period. It is calculated for each engine and any date range, and compared with the previous period.
Which scores sit next to visibility?
| Score | What it tells you | Calculation |
|---|---|---|
| Visibility | How often AI names you | Answers that name the brand, divided by all answers in the period |
| Share of voice | Your share of all brand mentions in the answers | Mentions of the brand, divided by mentions of all tracked brands |
| Average position | Where you come when AI lists options | Average order in which the brand is first named, where 1 is first |
| Sentiment | Whether AI talks about you warmly, neutrally or critically | Positive 100, neutral 50, negative 0, averaged across mentions |
What does the calculation look like with numbers?
Say you track 20 prompts in one market. ChatGPT is checked daily, so 30 days give 600 answers. If 150 of those answers name your brand, your ChatGPT visibility for the period is 150 divided by 600, or 25%.
If the same 600 answers contain 1,000 mentions of tracked brands and 150 are yours, your share of voice is 15%. These figures are an illustration, not customer data.
How precise is the number?
Your report shows a 95% confidence range for visibility, the band the true figure most likely sits in, next to the number of answers behind it. At 50% visibility, 20 answers give a range of about 30% to 70%, and 400 answers narrow it to about 45% to 55%.
For a method you can run by hand, with sample sizes, read how to measure AI visibility.
What is left out of the calculation?
- Questions that name your brand: left out by default, so the score is not inflated.
- Searches with no AI Overview: stored separately and kept out of visibility, so a missing Overview never counts against you.
- Weak mentions: a mention without a supporting quote, or below 50% confidence, does not count.
- New competitors: a competitor is scored only on answers collected after you start tracking it.