Micro-Agent Concepts & Architecture

Definition

A micro-agent is a highly focused AI agent with 1-3 steps designed to accomplish a single, well-defined task. Unlike traditional monolithic agents that try to handle entire workflows, micro-agents embrace the Unix philosophy: “do one thing and do it well.”

Core Architecture

Traditional Agent (Monolithic):
┌─────────────────────────────────┐
│  Research + Analyze + Report    │  ← 10-15 steps, complex logic
│  (All in one agent)             │  ← High context usage
└─────────────────────────────────┘

Micro-Agent Chain:
┌─────────┐     ┌─────────┐     ┌─────────┐
│Research │ --> │ Analyze │ --> │ Report  │  ← 2-3 steps each
│ Agent   │     │ Agent   │     │ Agent   │  ← Focused context
└─────────┘     └─────────┘     └─────────┘

How chaining actually works

1. Agent creation phase

// Agent 1: Data Collector
{
  name: "daily-sales-collector",
  steps: [
    {
      description: "Connect to Salesforce and pull today's sales data",
      requiresVerification: false
    },
    {
      description: "Format data into structured JSON with key metrics",
      requiresVerification: false
    },
    {
      description: "Run the 'sales-analyzer' agent with the formatted data",
      requiresVerification: false
    }
  ]
}

2. Runtime execution

Step 1 & 2 execute normally using available tools
Step 3 triggers findAndRunAgent tool internally
The AI recognizes “Run the X agent” pattern and converts to tool call
New chat is created for the downstream agent
Context is passed via the instructions parameter

3. Context flow

Agent 1 Output: {sales: $45K, leads: 23, conversions: 5}
                         ↓
Agent 2 receives this as initial context
                         ↓
Agent 2 Output: {trend: "up 15%", anomalies: [...]}
                         ↓
Agent 3 receives cumulative insights

Benefits over monolithic agents

Aspect	Monolithic	Micro-Agent Chain
Token Usage	High (full context)	Low (scoped context)
Failure Recovery	Restart entire flow	Restart single agent
Debugging	Complex traces	Isolated logs
Human Review	Overwhelming	Focused chunks
Reusability	Limited	High (mix & match)
Cost	Higher	40-60% lower

Implementation patterns

Sequential chain

[Extract] → [Transform] → [Load] → [Validate]

Branching chain

            ┌→ [Email Report]
[Analyze] ──┤
            └→ [Slack Alert]

Convergent chain

[Source A] ─┐
            ├→ [Aggregate] → [Report]
[Source B] ─┘

Technical implementation details

When an agent step contains text like “run the X agent”, the system:

Pattern Recognition: The AI model identifies agent execution intent
Tool Invocation: Calls findAndRunAgent with:
- agentName: Extracted from the step description
- instructions: Output from current agent’s execution
- addContext: Set to true to include recent messages
Chat Creation: New chat is spawned with:
- Title: “Execution of [Agent Name] - triggered by [Parent Agent]”
- Initial context: Instructions + any passed data
Execution: Child agent runs in isolation with its own:
- Token budget
- Tool access
- Execution logs
- Error handling

Best practices for micro-agent design

Single Responsibility: Each agent should have ONE clear purpose
Clear Naming: Use descriptive names like “invoice-validator” not “agent-1”
Explicit Outputs: Define what data the agent produces
Error Handling: Include fallback steps for common failures
Idempotency: Agents should be safe to re-run

Example: complete sales pipeline

Micro-Agent 1: lead-scraper
  Step 1: Search LinkedIn for matching prospects
  Step 2: Extract contact information
  Step 3: Run 'lead-enricher' with the contact list

Micro-Agent 2: lead-enricher
  Step 1: Look up company information for each lead
  Step 2: Score leads based on ICP criteria
  Step 3: Run 'outreach-drafter' with qualified leads

Micro-Agent 3: outreach-drafter
  Step 1: Generate personalized email for each lead
  Step 2: Schedule emails in outreach tool
  Step 3: Run 'campaign-tracker' to monitor opens

Micro-Agent 4: campaign-tracker
  Step 1: Check email open/click rates hourly
  Step 2: Flag hot leads for immediate follow-up
  Step 3: Generate daily performance report

Each agent is reusable - you could swap ‘outreach-drafter’ for ‘linkedin-messenger’ without touching the other agents.

Context Management & Verification - How context flows between agents
KPI Monitoring - Using search-chat-history for performance tracking
Multi-User Verification - Distributed approval workflows
Advanced Use Cases - Creative applications and optimization tips

Need help implementing micro-agent chains? Check our agent creation guide or contact support.

Micro-Agent Chaining Context Management & Verification

⌘I

Getting Started

Chats

AI Models

AI Agents

AI Tools

Files & Memory

Integrations

Legal AI

Model Context Protocol

Collaboration

Evaluation System

Micro-Agent Patterns

Organization Management

Enterprise

Account Settings

Tokens & Billing

Limits & Quotas

Security & Privacy

Videos

Support

Legal

API Reference

Micro-Agent Concepts & Architecture

Definition

Core Architecture

How chaining actually works

1. Agent creation phase

2. Runtime execution

3. Context flow

Benefits over monolithic agents

Implementation patterns

Sequential chain

Branching chain

Convergent chain

Technical implementation details

Best practices for micro-agent design

Example: complete sales pipeline

​Definition

​Core Architecture

​How chaining actually works

​1. Agent creation phase

​2. Runtime execution

​3. Context flow

​Benefits over monolithic agents

​Implementation patterns

​Sequential chain

​Branching chain

​Convergent chain

​Technical implementation details

​Best practices for micro-agent design

​Example: complete sales pipeline

​Related documentation

Definition

Core Architecture

How chaining actually works

1. Agent creation phase

2. Runtime execution

3. Context flow

Benefits over monolithic agents

Implementation patterns

Sequential chain

Branching chain

Convergent chain

Technical implementation details

Best practices for micro-agent design

Example: complete sales pipeline

Related documentation