AgentUse - Autonomous Agents That Work Without You

Experimental Feature: Manager agents are experimental. The configuration and behavior may change or be removed in future versions. Discuss feedback in GitHub Discussions.

What are Manager Agents?

Manager agents are specialized agents designed for orchestration. Instead of doing work directly, they coordinate teams of subagents, track progress, and make decisions about what work to delegate next.

When to Use Manager Agents

Use a manager agent when you need to:

Coordinate multiple specialists - Different agents for research, writing, review, etc.
Track complex workflows - Multi-phase projects with dependencies
Run scheduled operations - Regular tasks that span multiple runs
Maintain state across runs - Track what’s done, what’s pending, what’s blocked

Basic Configuration

Set type: manager in your agent frontmatter:

---
model: anthropic:claude-sonnet-5
type: manager
subagents:
  - path: ./researcher.agentuse
  - path: ./writer.agentuse
---

# Content Manager

## Goal
Create articles on trending topics.

## SOP
1. Research trending topics
2. Write articles for each topic
3. Review and publish

Configuration Options

Required

type: manager - Enables manager mode with orchestration prompts

Optional

schedule - Cron expression for scheduled runs

The Manager Prompt

When type: manager is set, your agent automatically receives instructions with orchestration guidelines. You don’t need to write these yourself - they’re included automatically.

Automatic Orchestration Loop

The manager follows this loop automatically (shown for reference - you don’t need to include this in your agent file):

UNDERSTAND - Parse goal and SOP from your instructions
CHECK - Review current state (pending work, in-progress items)
DECIDE - Determine what needs to happen next based on goal and state
DELEGATE - Call subagents with clear, specific instructions
TRACK - Update store items with outcomes from delegation
REPEAT - Continue until the goal is achieved or no further progress can be made

This means you only need to define your Goal and SOP - the manager handles the orchestration mechanics.

Schedule Awareness

If your manager has a schedule, it receives context about run frequency:

---
type: manager
schedule: "0 9 * * *"  # Daily at 9 AM
---

The manager learns to pace work appropriately - not rushing to complete everything in one run if there’s time, checking progress vs targets before starting new work.

Work Tracking with Store

Managers work best with a persistent store:

---
type: manager
store: "my-project"  # Shared store name
subagents:
  - path: ./researcher.agentuse
  - path: ./writer.agentuse
---

All subagents can share the same store by using the same store name. This enables coordination without explicit communication.

See Store Guide for available store tools.

Writing SOPs (Standard Operating Procedures)

A good SOP clearly defines the workflow phases:

## SOP (Standard Operating Procedure)

### Phase 1: Research
- Use the researcher to find 3 interesting topics
- Store each topic with type "topic" and status "pending"

### Phase 2: Writing
- For each pending topic, delegate to the writer
- Update status to "in_progress" when started
- Update status to "written" when complete

### Phase 3: Review
- For each written article, delegate to the reviewer
- If approved, update status to "done"
- If revisions needed, send back to writer

### Completion
- All items should have status "done"
- Summarize completed work

Complete Example: Content Team

Manager Agent

# manager.agentuse
---
model: anthropic:claude-sonnet-5
type: manager
store: "content-pipeline"
schedule: "0 * * * *"  # Every hour
subagents:
  - path: ./agents/researcher.agentuse
  - path: ./agents/writer.agentuse
  - path: ./agents/reviewer.agentuse
---

# Content Team Manager

## Goal
Produce 3 high-quality articles per day.

## SOP

### Phase 1: Topic Discovery
- Check store for pending topics
- If fewer than 3 pending topics, use researcher to find more
- Store topics with type "topic", status "pending"

### Phase 2: Writing
- For each pending topic, delegate to writer
- Pass topic context and target word count (500 words)
- Store article with type "article", parentId = topic id

### Phase 3: Review
- For each unreviewed article, delegate to reviewer
- If approved, mark article as "done"
- If revisions needed, mark as "needs_revision" with feedback

### Completion Criteria
- 3 articles with status "done" today
- Report progress and any blockers

Researcher Subagent

# agents/researcher.agentuse
---
model: anthropic:claude-haiku-4-5
store: "content-pipeline"
---

You are a research specialist. Find trending topics.

When given a research task:
1. Search for trending topics in the specified area
2. Evaluate each topic for article potential
3. Create store items for promising topics

Return a summary of topics found.

Writer Subagent

# agents/writer.agentuse
---
model: anthropic:claude-sonnet-5
store: "content-pipeline"
---

You are a content writer. Create engaging articles.

When given a writing task:
1. Get the topic from the store using the provided ID
2. Research and write a compelling article
3. Create a store item for the article linked to the topic
4. Update the topic status to "written"

Return the completed article.

Reviewer Subagent

# agents/reviewer.agentuse
---
model: anthropic:claude-haiku-4-5
store: "content-pipeline"
---

You are an editor. Review articles for quality.

When given a review task:
1. Get the article from the store
2. Check for: accuracy, clarity, engagement, grammar
3. Either approve (update status to "done") or request revisions

Return your review decision with feedback.

Delegation Guidelines

When managers delegate to subagents:

Provide Clear Instructions

Be specific about what you need. Include context from previous work.

writer({
  task: "Write a 500-word article about AI productivity tools",
  context: { topicId: "...", keywords: [...], targetAudience: "..." }
})

Pass Store Item IDs

So subagents can update the same items:

reviewer({
  task: "Review article for publication",
  context: { articleId: "01HX...", topicId: "01HW..." }
})

Set Clear Expectations

What output do you expect? What quality bar?

task: "Write article. Must include: 3 actionable tips, real examples, conclusion with CTA"

Handling Blockers

Managers should stop and report when blocked:

## When Blocked

If I need human input, I will:
1. State what I'm blocked on
2. Explain what decision/input I need
3. List available options if applicable

Example blockers:
- Need approval for topic selection
- External resource required (API key, credentials)
- Quality issue that requires human judgment

Best Practices

Single Responsibility

Each subagent should have one clear purpose

State in Store

Track all work items in the store, not in prompts

Clear SOPs

Define phases, transitions, and completion criteria

Pace with Schedule

Don’t rush if you run frequently

Debugging Manager Agents

Enable Verbose Logging

agentuse run manager.agentuse --verbose

Check Store State

# View store contents
cat .agentuse/store/content-pipeline/items.json | jq

Test Subagents Independently

# Run subagent directly
agentuse run ./agents/writer.agentuse "Write about AI tools"

Next Steps

Store Guide

Learn about persistent data storage

Scheduling

Run managers on a schedule

Sub-Agents

Deep dive into subagent configuration

Examples

See complete manager examples

Getting Started

Building

Running

Reference

Manager Agents

What are Manager Agents?

When to Use Manager Agents

Basic Configuration

Configuration Options

Required

Recommended

Optional

The Manager Prompt

Automatic Orchestration Loop

Schedule Awareness

Work Tracking with Store

Writing SOPs (Standard Operating Procedures)

Complete Example: Content Team

Manager Agent

Researcher Subagent

Writer Subagent

Reviewer Subagent

Delegation Guidelines

Handling Blockers

Best Practices

Single Responsibility

State in Store

Clear SOPs

Pace with Schedule

Debugging Manager Agents

Enable Verbose Logging

Check Store State

Test Subagents Independently

Next Steps

Store Guide

Scheduling

Sub-Agents

Examples

​What are Manager Agents?

​When to Use Manager Agents

​Basic Configuration

​Configuration Options

​Required

​Recommended

​Optional

​The Manager Prompt

​Automatic Orchestration Loop

​Schedule Awareness

​Work Tracking with Store

​Writing SOPs (Standard Operating Procedures)

​Complete Example: Content Team

​Manager Agent

​Researcher Subagent

​Writer Subagent

​Reviewer Subagent

​Delegation Guidelines

​Handling Blockers

​Best Practices

Single Responsibility

State in Store

Clear SOPs

Pace with Schedule

​Debugging Manager Agents

​Enable Verbose Logging

​Check Store State

​Test Subagents Independently

​Next Steps

Store Guide

Scheduling

Sub-Agents

Examples

What are Manager Agents?

When to Use Manager Agents

Basic Configuration

Configuration Options

Required

Recommended

Optional

The Manager Prompt

Automatic Orchestration Loop

Schedule Awareness

Work Tracking with Store

Writing SOPs (Standard Operating Procedures)

Complete Example: Content Team

Manager Agent

Researcher Subagent

Writer Subagent

Reviewer Subagent

Delegation Guidelines

Handling Blockers

Best Practices

Debugging Manager Agents

Enable Verbose Logging

Check Store State

Test Subagents Independently

Next Steps