Pipelines
Agents in Pipelines
Use agents as pipeline stages.
Agents fit best in pipelines when a stage needs model reasoning, tools, retrieval, or instructions. Keep the orchestration in the pipeline and the model behavior on the agent.
1. Build a Focused Agent
const triageAgent = new AgentBuilder("triage", model)
.instructions("Classify the urgency of support tickets.")
.defaultMaxTurns(2)
.build();2. Format the Prompt in a Step
const pipeline = new PipelineBuilder<string>()
.step((ticket) => `Classify this ticket:\n\n${ticket}`)
.prompt(triageAgent)
.build();The pipeline owns the changing input. The agent owns the stable instructions.
3. Use Agent Tools Normally
const supportAgent = new AgentBuilder("support", model)
.instructions("Look up account details before answering account questions.")
.tool(lookupAccount)
.defaultMaxTurns(3)
.build();
const pipeline = new PipelineBuilder<string>()
.step((ticket) => `Answer this support ticket:\n\n${ticket}`)
.prompt(supportAgent)
.build();The agent can call tools during the prompt step. The pipeline receives the final agent output.
4. Use Separate Agents for Separate Jobs
const pipeline = new PipelineBuilder<string>()
.parallel({
customerReply: new PipelineBuilder<string>().prompt(replyAgent).build(),
internalSummary: new PipelineBuilder<string>().prompt(summaryAgent).build(),
})
.build();Separate agents make instructions, tools, and traces easier to reason about.