Skip to main content
An agent is one LLM step in the workflow graph.

Agent properties

Uses

uses declares external capabilities and context available to the agent. It can include tools, prompts, and resources.

File directive

file uploads content before the agent executes and injects the resulting file attachment into the agent’s chat history. The content expression is positional and required; an optional block sets name and purpose.

File syntax

The block { ... } is optional. When omitted, defaults apply.

File properties

The content expression accepts references (agent.summarizer, dynamic.data), string literals ("manual content"), and number literals (132).

Content from an agent

Inline content

Multiple files

Multiple file directives are allowed on a single agent:

Agent loops

Use for ... in when each item in a collection should be processed with the same agent.
Loop headers may destructure object-shaped items:
The output of a looped agent is an array of that agent’s output objects.

Context continuation

Use context: agent.some_agent when a later agent should continue from an earlier agent’s message history.
A structured reference such as agent.investigate_task.issue reads an output value. context: agent.investigate_task passes the prior conversation/message history so the next agent can append a new instruction and continue the work.