Sequential Agents

Ordered Processing: Each step builds on the previous agent&#x27;s output
Predictable Flow: Deterministic execution order for reliable workflows
Context Continuity: Information flows naturally through the conversation
Specialized Roles: Each agent can focus on its specific expertise

Sequential agents execute sub-agents one after another in a predetermined order, creating predictable pipeline workflows where each step builds on the previous one.

Quick Example

Here's how to create a research pipeline that processes information through multiple sequential steps:

// Create specialized agents for each step
const researchAgent = new LlmAgent({
  name: "researcher",
  model: "gemini-2.5-flash",
  tools: [new GoogleSearchTool(), new WikipediaTool()],
  instruction: "Gather comprehensive information about the topic",
});

const analysisAgent = new LlmAgent({
  name: "analyst",
  model: "gemini-2.5-flash",
  instruction: "Analyze the research data and identify key insights",
});

const summaryAgent = new LlmAgent({
  name: "summarizer",
  model: "gemini-2.5-flash",
  instruction: "Create a concise summary with actionable recommendations",
});

// Create sequential pipeline that runs research → analysis → summary
const { runner } = await AgentBuilder
  .create("research-pipeline")
  .withDescription("Comprehensive research pipeline with analysis and summary")
  .asSequential([researchAgent, analysisAgent, summaryAgent])
  .build();

// Each agent processes the output from the previous one
const result = await runner.ask("Analyze the current state of renewable energy adoption");