Chapters
Chapters are titled sections that cover the whole video, back to back. Each has a start and end time, a title, a short summary, the words said and a description of what is shown. They suit navigation: a list of matches in a tournament replay, or the segments of a news show. Chapters appear in three places:- In the page block, as
Clipitems underhasPartin the JSON-LD. Search engines show these as key moments. - In the ARV record, under
chapters. - In the account API, from
GET /v1/videos/{video_id}/timeline, with the shots, speaker turns and on-screen text around them.
Moments
A moment is the span that answers one question. It can be shorter than a chapter, or cross two. Search finds moments by what is said, what is shown and what is written on screen, not by text alone. Every search result carries:- Start and end. Seconds in JSON-LD responses, milliseconds in the ARV record and the account API.
- The evidence. The timed sentence or on-screen text that matched.
- A confidence band.
high: the evidence holds the query and a second, independent signal agrees.medium: the second signal is strong, or both signals agree weakly. Check it before you show it. Search never serveslowresults.
medium result with no matched sentence as no match. An empty result means the library has no answer: say so and do not guess.
Full videos, not pre-cut clips
Import the full-length video, such as a four hour event replay. AgentTV finds the matches, runs and segments inside it. You do not need to cut and publish separate clips for AI apps to find a single moment. When your team needs one range as a file, see range links.Linking to a moment
Every moment opens at its start second:- On the AgentTV watch page, with
?t=<seconds>. - In your own player, with your player’s start parameter. See Start at the moment.
- In an AI app, through the playback call, which signs a session that starts at the moment. See Play a moment in an AI app.