Canvas

A canvas is a structured output object: text, charts, images, tables, logs, tasks, widgets, actions, data, and metadata. It is the thing the agent produced.

Requirements

A useful canvas must be:

Requirement	Meaning
Renderable	It can be shown as UI
Addressable	Parts can be referenced by stable IDs and paths
Updatable	Parts can be patched during or after an agent run
Consumable	Other systems can read stable exported values
Auditable	Source, actor, version, and provenance survive

Static canvas

Static canvases are best for reports, audits, research summaries, client deliverables, and one-time agent results.

Agent produces full canvas JSON
-> Hub stores snapshot
-> Link opens viewer

Live canvas

Live canvases are best for long-running agent runs, monitoring dashboards, workflow status, research dossiers, debugging sessions, and mini-apps.

Agent creates initial canvas
-> Agent sends patch events
-> Hub stores event log
-> Viewer updates live
-> API consumers subscribe

Blocks are for humans

Blocks describe the human-facing surface: markdown, metrics, charts, tables, logs, and controls.

Exports are for machines

Exports expose stable paths that other systems can consume. API consumers should not scrape visual blocks.

Start

Core concepts

AgentCanvas

Protocol

Product strategy

Examples

Requirements

Static canvas

Live canvas

Blocks are for humans

Exports are for machines

​Requirements

​Static canvas

​Live canvas

​Blocks are for humans

​Exports are for machines

Requirements

Static canvas

Live canvas

Blocks are for humans

Exports are for machines