Multi-Agent Workflows - Aster Agents

Overview

Multi-agent workflows in Aster Agents allow you to create collaborative systems where specialized agents call each other to handle complex, multi-step tasks. Instead of building one agent that tries to do everything, you can create focused agents that excel at specific functions and coordinate their work automatically.

How It Works

Multi-agent coordination is powered by the call_agent tool. When you configure an agent to work with others, Aster Agents handles the wiring automatically.

Provides Agent Context

The calling agent receives information about available agents in its system prompt.

Maintains Conversation Threads

Agents can continue conversations across multiple interactions.

Preserves Context

Information flows seamlessly between agents in the workflow.

Handles Permissions

Only allows calls to explicitly configured agents.

The Call Agent Tool

The call_agent tool enables agents to:

Send messages to other specific agents
Continue existing conversation threads
Delegate specialized tasks
Build complex workflows through agent collaboration

Setting Up Multi-Agent Workflows

Configure Agent Relationships

In the Control Hub when creating or editing an agent:

Enable the Call Agent Tool: Add call_agent to your agent’s available tools
Select Callable Agents: Choose which other agents this agent can invoke from your organization’s agent list
Automatic Integration: Agent details are automatically added to the system prompt

Agent Information Integration

When an agent has callable agents configured, they automatically receive:

Agent Names: Human-readable identifiers for each callable agent
Agent IDs: Technical identifiers needed for the call_agent tool
Agent Descriptions: Understanding of each agent’s capabilities and specializations

This information appears in the system prompt like this:

You have access to the following agents that you can call using the call_agent tool:

- Data Analyst (ID: 123)
  Description: Specializes in analyzing sales data and creating insights

- Report Writer (ID: 456)
  Description: Creates professional reports and presentations from data analysis

When using the call_agent tool, you must provide the agent_id from the list above.

Design Your Workflow

Plan how agents will work together:

Define Roles: What specific task does each agent handle?
Map Information Flow: What information needs to pass between agents?
Plan Entry Points: Which agent do users interact with first?
Consider Threading: When should agents continue existing conversations vs. start new ones?

Common Workflow Patterns

Sequential Processing

Agents work in a defined order, each building on the previous agent’s work.Example: Research to Report Pipeline

Research Agent → Gathers information from web and knowledge bases
Analysis Agent → Processes findings and identifies key insights
Writer Agent → Creates formatted report from analysis
Review Agent → Quality checks and provides final output

Specialized Task Delegation

A primary agent delegates specific subtasks to specialized agents.Example: Customer Support Triage

Support Agent receives customer inquiry
Based on issue type, calls:
- Technical Agent for product issues
- Billing Agent for payment questions
- Account Agent for user management
Support Agent synthesizes response for customer

Parallel Processing with Coordination

Multiple agents work simultaneously, with results combined by a coordinator.Example: Market Research Workflow

Coordinator Agent breaks down research request
Calls multiple agents in parallel:
- Web Research Agent → Industry trends
- Data Agent → Internal sales data
- Competitor Agent → Competitive analysis
Coordinator Agent combines all findings into comprehensive report

Iterative Refinement

Agents work together through multiple rounds to refine outputs.Example: Content Creation Loop

Writer Agent creates initial draft
Editor Agent provides feedback and suggestions
Writer Agent revises based on feedback (using thread ID to continue conversation)
Process repeats until quality standards are met

Practical Examples

Sales Intelligence
Content Production
Data Analysis

Prospect Researcher (Entry Point)
├── Data Collector → Gathers company information
├── Social Media Analyst → Reviews social presence
├── News Tracker → Finds recent company updates
└── Sales Strategist → Combines insights into outreach plan

Content Manager (Entry Point)
├── Topic Researcher → Identifies trending subjects
├── Writer → Creates initial content
├── SEO Optimizer → Enhances for search
├── Social Media Adapter → Creates platform-specific versions
└── Publisher → Schedules and distributes content

Data Coordinator (Entry Point)
├── Data Collector → Extracts from databases/APIs
├── Cleaner → Processes and validates data
├── Analyst → Performs statistical analysis
├── Visualizer → Creates charts and graphs
└── Reporter → Compiles findings into presentation

Best Practices

Agent Design

Single Purpose: Each agent should excel at one specific type of task
Clear Descriptions: Write detailed agent descriptions since these appear in system prompts
Consistent Interfaces: Design agents to work well together
Error Handling: Consider what happens when agents can’t complete tasks

Workflow Planning

Start Simple: Begin with 2-3 agents and expand gradually
Map Dependencies: Understand which agents need outputs from others
Plan for Failures: What happens if an agent in the chain fails?
Test Thoroughly: Run complete workflows manually before deploying

Communication Design

Clear Handoffs: Agents should know exactly what information to pass along
Context Preservation: Use thread IDs to maintain conversation context when needed
Status Updates: Keep users informed about multi-step progress
Result Integration: Plan how final outputs get assembled and presented

Performance Considerations

Parallel vs Sequential: Choose based on dependencies and urgency
Thread Management: Use conversation threads strategically to maintain context
Token Efficiency: Monitor cumulative token usage across agent calls
User Experience: Balance thoroughness with response time

Managing Multi-Agent Systems

Configuration Management

Agent Permissions: Carefully control which agents can call which others
Role Clarity: Ensure each agent’s purpose is clearly defined and documented
Version Control: Track changes to agent configurations and relationships

Monitoring and Optimization

Workflow Performance: Monitor how long complete workflows take
Agent Utilization: Track which agents are called most frequently
Success Rates: Measure how often workflows complete successfully
User Feedback: Collect input on workflow quality and usefulness

Troubleshooting Common Issues

Context Loss: Information getting lost between agent handoffs
Circular Calls: Agents calling each other in loops
Permission Errors: Agents trying to call agents they don’t have access to
Thread Management: Confusion about when to start new threads vs continue existing ones

Getting Started

Your First Multi-Agent Workflow

Identify a Multi-Step Task

Choose something that naturally breaks into distinct phases.

Create Specialized Agents

Build 2-3 agents that handle different aspects.

Configure Relationships

Set up which agents can call which others.

Test the Flow

Run through the complete workflow manually.

Refine and Expand

Improve based on results and add complexity gradually.

Simple Starter Workflows

Research → Analysis → Report

Great for information gathering and synthesis.

Draft → Review → Revise

Perfect for content creation and quality control.

Collect → Process → Visualize

Ideal for data analysis tasks.

Triage → Specialize → Resolve

Excellent for customer support scenarios.

Multi-agent workflows unlock the full potential of AI collaboration, allowing you to create sophisticated systems that handle complex tasks through intelligent coordination between specialized agents.

​Overview

​How It Works