The Problem
AI agents can reason about text brilliantly. But show them a 30-minute meeting recording and ask “what did the client say about pricing?” - they fail. Video files are opaque blobs. Your agent can’t query them, can’t search them, can’t get timestamped answers from them.The Platform Loop
Every VideoDB workflow follows the same pattern:Quick Example
See: Three Input Types
Video or an RTStream the same way.
Understand: Indexes Are Everything
Indexes are what transform opaque media into searchable knowledge. You create them with prompts.Spoken Index
Transcribes audio and makes it searchable:Visual Index
Understands what’s happening on screen:Multiple Indexes
Create different perspectives on the same media:Search Returns Evidence
Search returns timestamps and playable links - not just “found” but verifiable.Act: Events, Alerts, Editing
Trigger on conditions
Compose with code
Objects at a Glance
Next Steps
Quickstart
Try it hands-on
Core Concepts (Full)
Deep dive with examples
Data Model
All objects and relationships
Indexes & Search
How indexing and retrieval work