What it measures
- Visibility. How often AI apps point people to your video when they answer questions about your topics. Each number is a count of answers, such as “8 of 35 answers”.
- Readiness. Nine checks on your website, from AI agents opening your pages to playback and usage reporting, rated in levels from Level 0 (Not ready) to Level 5 (Agent-Ready).
The AI apps it asks
ChatGPT, Claude, Gemini, Perplexity and Grok, each through its API with web search on, plus Google AI Overviews and Google AI Mode, read from a Google search page. Every answer is a new conversation, asked from the US in US English. The questions never name your brand or your videos.Run it
1
Add your brand
In the console, open Visibility, or call
POST /v1/visibility/brands with your website, YouTube channel or name. The first report starts at once and is free.2
Set the questions you care about
By default, AgentTV picks questions from your own videos. To track your own, call
POST /v1/visibility/brands/{brand_id}/questions with 1 to 10 questions of 6 to 20 words each. They are asked every week on every AI app. A new list starts a new trend line.3
Publish, then compare
Your first full report is the baseline. Your tracked questions run every week. AgentTV also runs a full report again at day 30 and day 90, on the same AI apps. Refresh any time, once a day, with
POST /v1/visibility/brands/{brand_id}/refresh.GET /v1/visibility. Each brand comes with its readiness, its latest report, its history, and a list of fixes per question: whether AI apps cite you, which of your moments should answer, and what is missing.
Read the numbers with care
- AI answers change from run to run. Read one report as a sample, and compare reports over time.
- Crawl-time changes take weeks to show. See Crawl time and inference time.
- No one can promise a citation. AI apps decide what they cite.