Glossary
Agent-readable recording terms
The core vocabulary for agent-readable recordings and the AREC format. One definition per term.
- AREC (Agent Recording)
- AREC (Agent Recording) is the open markdown format that encodes a screen recording as text an AI agent reads instead of watching video.
- Agent-readable recording
- An agent-readable recording is a screen recording whose share link doubles as a structured text document (summary, key moments, click targets, and transcript) that AI agents can read instead of watching video.
- Markdown twin
- A markdown twin is the structured text document an agent-readable recording produces, holding the summary, key moments, click targets, transcript, and metadata in one file.
- Key moment
- A key moment is a timestamped instant in an agent-readable recording, carrying an extracted frame, a click target, and a plain-language description of what happened.
- Click target
- A click target is the UI element interacted with at a key moment, recorded as a plain-language description plus its x and y coordinates.
- Agent legibility
- Agent legibility is how readable a piece of work is to an AI agent, measured by how much it can act on without human translation.
- Proof of agent work
- Proof of agent work is a recording that documents what an AI agent did on screen, captured as a readable AREC document others can review.
- Agent context
- Agent context is the structured information an AI agent needs to understand a situation and act, such as what happened on screen, when, and where.
New to the idea? Start with what is an agent-readable recording.