Depra AI takes the questions your buyers ask ('best body balm under ₹3,000'), asks them to ChatGPT, Gemini, Perplexity, Google AI Overviews and every other AI engine you track, from inside your chosen country, stores every full answer, and records whether each answer named you, in what order, in what tone, and which web pages it cited. Scores are computed from those stored answers, with the number of answers behind them attached.
This page sets out each step, the rules that decide what counts, and the limits of the method. A prompt here means one buyer question that Depra AI tracks.
Which AI engines does Depra AI check, and how are answers captured?
Every plan checks ChatGPT, Gemini, Perplexity and Google AI Overviews, all daily, and Enterprise can add every other major AI engine as an add-on. ChatGPT and Gemini answers are captured from the consumer web interfaces at chatgpt.com and gemini.google.com, so you see the answers real people see there. Google AI Overviews, the AI-written summary Google shows above some results, are read from a real Google results page. Perplexity is checked through Sonar, its own answer model with live web search.
The step-by-step capture process is in how Depra AI captures AI answers.
| Engine | What is captured | How often |
|---|---|---|
| ChatGPT | The answer shown in the chatgpt.com web app, with web search switched on so it cites sources | Daily |
| Gemini | The answer shown in the gemini.google.com web app | Daily |
| Google AI Overviews | The AI Overview block on a real Google results page for the query in that country, its source links, and whether an Overview appeared at all | Daily |
| Perplexity | The answer from the Sonar model with live web search, set to the country | Daily |
Every engine in the table is checked daily, on every plan. Daily checks are scheduled for 02:30 IST.
Where are the questions asked from?
Each question is asked from inside the country you choose, at country level. Depra AI supports 40 markets: India, the United States, the United Kingdom, Ireland and 29 other European countries, 6 Gulf countries and Australia.
A project can track up to 10 markets. A prompt tracked in 2 markets uses 2 of your plan's prompts.
Depra AI does not target cities, simulate personas or use a logged-in account with chat history. You can write a city into a question, but it is still asked from the country as a whole. Every check is a fresh question from that country with no personal history, so every day's checks run under the same conditions and can be compared.
Which questions are counted?
When you set up a project, Depra AI suggests 5 topics with 8 buying questions each, 40 in total, written the way a buyer would type them. None of the suggested questions name your brand. You can add, edit, pause and tag prompts.
Depra AI tracks questions in English, Hinglish, French and most other major languages, plus code-mixed questions, on every plan, and Hinglish is its speciality. When India is one of your markets, Depra AI also suggests Hinglish versions. Hinglish is Hindi and English typed in English letters, and Depra AI always writes it in the Latin alphabet.
Prompts that already contain your brand name are left out of your scores by default. A question like 'is Brand X any good?' almost always returns Brand X, so counting it would inflate visibility.
How are brand mentions read from each answer?
Depra AI reads every stored answer. For each tracked brand the answer names, it records four things.
- Position: the order in which the brand is first named, where 1 means named first.
- Sentiment: whether the answer describes the brand positively, neutrally or negatively.
- Quote: the exact sentence that names the brand, so you can check every mention.
- Confidence: how sure Depra AI is that the text refers to the brand.
What counts as a mention
- A brand is matched on its tracked names, which can include other spellings and its domain, so "depra.ai" can count as Depra AI.
- A brand name found inside a longer word does not count, so 'Ola' inside 'Motorola' is not a mention of Ola.
- A mention without a supporting quote from the answer is dropped.
- A mention below 50% confidence never counts towards any score.
- The language of each reply is detected separately from the language of the question, because engines often answer a Hinglish question in English.
How are the scores calculated?
Every score is computed from the stored answers in the date range you pick, and compared with the previous period. A competitor is only scored on answers collected after you started tracking it.
| 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 (AI share of voice explained) | Mentions of the brand, divided by mentions of all tracked brands |
| Average position | Where you come in the list when AI names options | Mean first-mention position across mentions of the brand |
| Sentiment | Whether AI talks about you warmly, neutrally or critically | Positive = 100, neutral = 50, negative = 0, averaged across mentions |
Answers where Google showed no AI Overview are excluded from every calculation above. See AI visibility tracking in Depra AI for how these scores appear in the app.
Confidence ranges and sample size
AI engines can name different brands when the same question is asked twice, which is covered in whether ChatGPT gives the same answer to everyone. So a score is only as precise as the number of answers behind it.
Your report shows a 95% confidence range for visibility, the band the true figure most likely sits in, next to the number of answers. At 50% visibility, 20 answers give a range of about 30% to 70%. 400 answers narrow it to about 45% to 55%.
What the daily brief reports
The daily brief is an in-app page that lists what changed since the previous scan day. It reports a visibility change only when the two days' 95% ranges do not overlap, and only when each day has at least 5 answers. Smaller moves are normal run-to-run noise and stay out of the brief.
What happens when Google shows no AI Overview?
Google does not show an AI Overview for every search. When no Overview appears, Depra AI stores that as its own result and keeps it out of visibility, so a missing Overview never counts as an answer that left you out.
How often Google showed an AI Overview at all is recorded for every Google check. It is not yet shown on a screen.
What happens at the monthly run ceiling?
Each plan has a monthly ceiling on runs, where one run is one engine answering one prompt in one market. Starter allows 2,000 successful checks a month, Growth 8,700, Scale 15,000 and Enterprise 37,500. Each allowance covers a daily check of every prompt slot on ChatGPT, Gemini, Perplexity and Google AI Overviews, at the full prompt count.
New checks pause when the allowance is used and resume next month. Saved reports stay available. Plan details are on Depra AI pricing.
What are the limits of this method?
- Engines not tracked on Starter, Growth and Scale: Google AI Mode, Claude, Microsoft Copilot, Grok, DeepSeek and Meta AI. Enterprise can add them as add-ons, set up by the Depra AI team.
- ChatGPT with search on: answers are captured with web search switched on, so answers a user gets with search off are not measured.
- Perplexity through its API: Perplexity answers come from the Sonar model with live search, which can differ from the Perplexity app.
- Cited pages only: Depra AI stores the pages an answer cites. It cannot see pages an engine read and chose not to cite.
- Keyword demand as a proxy: Where available, prompt volume uses measured monthly DataForSEO AI keyword demand for a short English term, or a broader category term. It does not count how often people ask the full sentence. Hinglish prompts use the English term. See what prompt volume means.
- Country level only: no city targeting, personas or logged-in chat history.
- Before and after only: when you mark an action done, Depra AI shows your visibility then and now. That comparison does not prove the action caused the change.
Where can I check Depra AI's published research?
Depra AI publishes open research with its data and code. The first study asked 10 buying questions (5 skincare, 5 fashion) in English and in Hinglish, 8 times each, to ChatGPT, Gemini and Perplexity from inside India: 480 answers, with fieldwork on 14 August 2026.
It measured how much each engine's brand list changed between English and Hinglish, beyond its normal rerun noise: 2.2 points for ChatGPT, 7.8 for Gemini and 23.4 for Perplexity in August 2026. A re-run of the same design on 13 October 2026 (479 answers) found 0.8 points for ChatGPT, 2.0 for Gemini, no longer significant, and 28.2 for Perplexity. Read the English vs Hinglish AI shopping study or check the study data and code on GitHub (opens in a new tab).
How Depra AI writes and checks what it publishes, including this page and its research, is set out in the Depra AI editorial policy.
FAQ
Does Depra AI use the ChatGPT app or the API?
The app. Depra AI records the answer shown in the chatgpt.com web interface, with web search switched on, asked from inside your chosen country. Gemini is captured the same way from gemini.google.com. The OpenAI API only approximates what the app shows, so Depra AI keeps it as a backup route. Perplexity is the exception: it is checked through its Sonar API.
How often does Depra AI check each engine?
Daily. ChatGPT, Gemini, Perplexity and Google AI Overviews are all checked daily, on every plan, with checks scheduled for 02:30 IST. Enterprise adds Claude, Microsoft Copilot, DeepSeek, Google AI Mode, Grok and more.
How accurate are Depra AI's scores?
Each score is as precise as the number of answers behind it. Your report shows a 95% confidence range for visibility and the answer count: at 50% visibility, 20 answers give a range of about 30% to 70%, and 400 answers about 45% to 55%. Every mention also carries the quoted sentence, so you can open the answer and check it.
Does Depra AI count questions that include my brand name?
Not by default. Prompts that already contain your brand name are left out of your scores, because asking about a brand by name almost always returns that name. Every question Depra AI suggests is written without your brand name.
