Sequential Agents

Sequential agents create powerful pipelines where agents execute in a specific order, with each step building on the results of the previous one. Think assembly line for AI - each agent specializes in one part of the process, and the final result is the combined output of all steps working together.

Perfect for workflows where order matters: research before analysis, writing before editing, data collection before processing. Unlike parallel agents that run simultaneously, sequential agents guarantee execution order and enable sophisticated multi-step reasoning.

Quick Start Example

Here's a market research pipeline that transforms a simple query into comprehensive business intelligence:

import { LlmAgent, SequentialAgent, WebSearchTool } from "@iqai/adk";

// Step 1: Gather raw data
const researchAgent = new LlmAgent({
  name: "market-researcher",
  model: "gemini-2.5-flash",
  instruction: `
    Research the given company/topic thoroughly. Focus on:
    - Current market position and competitors
    - Recent news and developments
    - Financial performance and growth trends
  `,
  tools: [new WebSearchTool()],
});

// Step 2: Analyze the collected data
const analysisAgent = new LlmAgent({
  name: "business-analyst",
  model: "gemini-2.5-flash",
  instruction: `
    Analyze the research data from the previous step. Identify:
    - Key opportunities and threats
    - Market trends and patterns
    - Competitive advantages and weaknesses
    Provide data-driven insights with specific examples.
  `,
});

// Step 3: Create actionable recommendations
const strategistAgent = new LlmAgent({
  name: "business-strategist",
  model: "gemini-2.5-flash",
  instruction: `
    Based on the research and analysis, create strategic recommendations:
    - 3-5 specific, actionable strategies
    - Risk assessment for each recommendation
    - Timeline and resource requirements
    Format as an executive summary.
  `,
});

// Sequential pipeline: research → analyze → strategize
const marketIntelligencePipeline = new SequentialAgent({
  name: "market-intelligence-pipeline",
  description: "Comprehensive market analysis and strategy development",
  subAgents: [researchAgent, analysisAgent, strategistAgent],
});

// Use the pipeline
const result = await marketIntelligencePipeline.run({
  message:
    "Analyze Tesla's position in the EV market and suggest growth strategies",
});

Visual Flow

How Sequential Processing Works

Sequential agents create a data pipeline where information gets progressively enriched at each step:

🔄 Execution Flow

1. Agent 1 receives the original input and processes it
2. Agent 2 gets both the original input AND Agent 1's output
3. Agent 3 receives original input + Agent 1's output + Agent 2's output
4. This continues for each agent in the sequence

💡 Context Accumulation
Each agent sees the full conversation history, so later agents can reference and build upon earlier agents' work. This creates sophisticated reasoning chains that single agents can't achieve.

🎯 Deterministic Order
Execution order is guaranteed - no race conditions or unpredictable results. Perfect for production workflows where consistency matters.

Real-World Use Cases

📊 Business Intelligence Pipeline
Research → Analysis → Strategic Recommendations → Executive Summary

📝 Content Creation Workflow
Draft → Fact-check → Edit → Style Review → Final Polish

🔍 Technical Documentation
Code Analysis → Documentation Draft → Technical Review → User Testing → Publication

⚖️ Legal Document Review
Initial Review → Compliance Check → Risk Assessment → Final Approval

🧪 Scientific Analysis
Data Collection → Statistical Analysis → Peer Review → Conclusion Generation

When to Choose Sequential Agents

✅ Choose Sequential When:

• Dependencies matter - Later steps need earlier results
• Quality control - Each stage validates and improves the work
• Specialization - Different expertise needed at each step
• Compliance - Regulated workflows requiring specific order
• Complex reasoning - Multi-step analysis and decision making

❌ Don't Use Sequential When:

• Tasks are completely independent
• Speed is more important than thoroughness
• You need real-time parallel processing
• Simple, single-step operations

Related Topics