Agents

Agents are LLM-backed actors that run a plan→act→observe loop, call their own tools, and remember across runs.

What an agent is

An agent has a system prompt, a default model, a set of actions/skills it can call, and long-term memory. During a run it loops: read the task, decide which tool to call, observe the result, and continue until the task is done or a step budget is hit.

Anatomy

FieldPurpose
System promptThe agent's role, voice, and instructions.
ModelWhich registered model it reasons with (provider-agnostic).
Actions & SkillsThe tools it may invoke (its allow-list / wired capabilities).
MemoryLong-term memory is on by default; toggle per agent via memory_config.longTerm.
VariablesReusable {{ name }} values injected into the system prompt.
CapsCost, time, and step budgets per run.

Agents inside workflows

An agent node runs the agent as one step of a workflow. The agent still calls its own tools mid-run; the workflow orchestrates what happens before and after. Its reply is available downstream as ${agent_output}.

The AI builder can create agents for you — give it a workflow description and it provisions the agents with the right tools and prompts.