Orchestration & Sub-Agents

Pattern

Sub-Agent Orchestrator

Custom Agent implementation demonstrating the Agent interface abstraction with an orchestrator that routes queries to specialized sub-agents (research, analysis, support). Shows options passing and structured outputs.

IntermediateNov 2025View the full pattern on desktop
Sub-Agent Orchestrator preview

Problems solved

  • Implement a custom Agent that routes to specialized sub-agents
  • Pass typed options into research, analysis, and support agents
  • Return structured outputs from the orchestrator layer
  • Delegate queries without collapsing specialists into one prompt

Use cases

  • Multi-agent support systems
  • Research versus analysis routing
  • Custom Agent interface tutorials
  • Specialist delegation architectures

AI SDK APIs

ToolLoopAgentcreateAgentUIStreamResponsetool(Output.objectstepCountIsgatewayInferAgentUIMessage

Tags

aiagentsorchestratorai-sdkcustom-agentsub-agentsroutingoptionsstructured-output

Requirements

Node.js
24+
Memory
512MB
Other
  • OpenAI API key
  • Exa API key

Environment variables

External services

openaiexa

Ready to use?

View the full interactive pattern with live preview and copy the source code.

View the pattern on desktop

Related patterns

Orchestrator-Worker Pattern preview

Orchestrator-Worker Pattern

Coordinate multiple worker agents for project management. Handles task distribution, progress tracking, and result synthesis.

aiagents+8
View pattern →
Research Agent Chain preview

Research Agent Chain

Sequential three-agent chain demonstrating structured outputs flowing between agents. Research Agent 1 gathers research, Expand Agent 2 expands research, Synthesis Agent 3 synthesizes final answer. Uses Exa tools and AI SDK 6's stabilized structured output support.

aiagents+8
View pattern →
Marketing Plan & Implement Agent preview

Marketing Plan & Implement Agent

Two-phase marketing agent with brand context: Stage 0 extracts brand info from URL or manual input, planning phase gathers requirements and creates a plan with todos, implementation phase executes the plan using web scraping and research tools. Uses callOptionsSchema + prepareCall for dynamic agent configuration.

aiagents+9
View pattern →
Branding Agent preview

Branding Agent

Extract brand design systems from any website using Firecrawl, then use AI tools to export tokens, generate color palettes, check accessibility, and analyze brand personality.

aiagents+8
View pattern →