Skip to main content
An agent is a session of an AI coding engine. One agent equals one engine session with a unique ID. Each agent has its own engine, model, and configuration.

​
What Makes Up an Agent

Every agent consists of:
  • Prompts - The instructions sent to the agent
  • Engine - The AI coding CLI that powers the agent
  • Model - The AI model the engine uses
  • Interactivity - Whether the agent waits for input or runs automatically
  • MCP - External tools and integrations available to the agent

​
Agent Types

Main Agent

Runs as a step in the workflow. Does the primary work.

Module

A main agent that can loop back to earlier steps.

Sub-agent

Spawned by main agents via MCP to delegate work.

Controller

Orchestrates on your behalf - answers questions, signals next steps.

​
When to Use Each Type

​
Main Agent

Use for standard workflow steps that run once and pass output forward.

Best for

  • Single-pass tasks (analysis, generation, implementation)
  • Steps that don’t need to revisit previous work
  • Most workflow steps

Configure Main Agents

Learn how to set up main agents

​
Module

Use when a step needs to loop back based on results.

Best for

  • Review and revision cycles
  • Iterative refinement
  • Quality gates that may require rework

Configure Modules

Learn how to set up modules

​
Sub-agent

Use to break complex work into delegated tasks within a single step.

Best for

  • Parallel task execution
  • Context isolation
  • Specialized subtasks
Sub-agents are not steps. They are a context management tool for delegating work between agents.

Configure Sub-agents

Learn how to set up sub-agents

​
Controller

Use for autonomous workflows where you want an agent to make decisions between steps.

Best for

  • Long-running autonomous workflows
  • Tasks where you want to review results, not manage process
  • Complex multi-step operations with clear objectives

Configure Controllers

Learn how to set up controllers

​
Agent vs Step

ConceptWhat It Is
StepA position in the workflow sequence
AgentThe AI session that executes at that position
Every step has exactly one agent. The step defines when to run. The agent defines how to run.

​
Engines

An engine is an AI coding CLI that powers the agent. Different engines have different capabilities, strengths, and supported models. Why this matters: You can mix engines in a single workflow—use one engine for creative tasks, another for complex reasoning, and a fast one for simple operations.

Configure Engines & Models

See available engines, model options, and configuration examples

​
Interactivity

Interactivity determines whether an agent waits for input or proceeds automatically.
Agent waits for user input.
  • Pauses after each prompt
  • User reviews and responds
  • Best for exploration and Q&A
This is how hybrid workflows work - some agents wait for you, others run automatically.

Configure Interactivity

Learn how to set interactive or non-interactive mode per agent

​
MCP

MCP (Model Context Protocol) servers extend agent capabilities with additional tools. What MCP provides:
  • Custom tool integrations
  • External data access
  • Sub-agent spawning
  • Signals for workflow control
The signals MCP is required for autonomous workflows where agents need to communicate with the controller. It’s also required when using sub-agents, since agent coordination works through MCP.

Configure MCP

Learn how to add MCP servers to your agents

​
Prompts

Prompts are the instructions sent to an agent. They define what the agent should do.

​
Chained Prompts

Multiple prompts injected into the same agent session, one after another. Instead of overwhelming one step with all instructions, you break it into smaller sequential prompts. Example flow:
  1. First prompt: “Analyze the codebase structure”
  2. User reviews output
  3. Second prompt: “Based on your analysis, identify potential issues”
  4. User reviews output
  5. Third prompt: “Create a plan to address the top 3 issues”
Same agent, same session. Prompts run in sequence. Common in interactive Q&A workflows.

Configure Chained Prompts

Learn how to set up sequential prompts for an agent

​
Placeholders

Placeholders inject data into agent prompts.
TypeSourceUse case
Static (packageDir)Pre-defined prompts from workflow packageShared prompts, split large prompts
Dynamic (userDir)Files created during workflowAgent A outputs a file, Agent B receives it
Built-in Placeholders: System data injected automatically - date, time, username, project name, selected tracks and conditions.

Configure Placeholders

Learn how to use static and dynamic placeholders in prompts

​
Directives

Directives allow agents to control the workflow by writing to a JSON file. The workflow listens after each step and takes action.
DirectiveAction
checkpointShows message to user, option to continue or stop
stopStops the workflow
errorShows error message and stops
pausePauses and waits for user input
loopReturns back to a previous step (modules only)
triggerTriggers any agent in the workflow (modules only)
Directives come from agents. Signals come from users. Both control execution, but from different sources.

Configure Directives

Learn how to enable agents to control workflow execution

​
Next Steps

Your First Workflow

Build a complete workflow from scratch

Build Agents

Configure agents for your workflow