Loading pattern preview
BlocksAgent Patterns
Sub-Agent Orchestrator
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.
Loading pattern preview
Problems solved
Technical challenges this implementation handles out of the box.
- 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
Products and workflows this pattern is designed to support.
- Multi-agent support systems
- Research versus analysis routing
- Custom Agent interface tutorials
- Specialist delegation architectures
Compare with
Similar patterns, and when each one is the better fit.
Research Agent ChainUse this when one agent doing all the research is too broad and you want separate gather, expand, and synthesize agents run in order with Exa search.
Orchestrator-Worker PatternUse this when an orchestrator agent built with Experimental_Agent must assign tasks to typed worker tools and report progress as it streams.
Eve Triage Orchestrator AgentUse this when one support message mixes intents and an Eve coordinator should split it across declared specialist subagents running in parallel.
Agent Routing PatternUse this when one chat endpoint should sort queries into specialist agents and fall back across OpenAI, Perplexity, and Deepseek if a provider fails.
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
- 2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
- 3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: OPENAI_API_KEY, EXA_API_KEY.
- 4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
- 5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route and verify responses.
Environment variables
Capabilities
AI SDK APIs
ToolLoopAgentcreateAgentUIStreamResponsetoolOutput.objectstepCountIsgatewayInferAgentUIMessageProviders
OpenAI
External services
Exa
Files added
8 files
app/sub-agent-orchestrator/page.tsxapp/sub-agent-orchestrator/layout.tsxapp/api/orchestrator/route.tscomponents/orchestrator-demo.tsxlib/orchestrator-agent.tslib/sub-agents.tslib/types.tsREADME.md
Dependencies
11 total
npm packages
7AISDK@exalabs/ai-sdklucide-reactNext.jsReactsonnerZod
Registry components
badgeemptybuttontooltip
Critical files
2 files
lib/orchestrator-agent.tsThe orchestrator agent is the core of this pattern: it implements the Agent interface, routes queries to specialized sub-agents, and handles options and structured outputs. The UI and API route are repeatable; this file is what users need to recreate the block's functionality.
lib/sub-agents.tsThe sub-agents define the specialized agent implementations (research, analysis, support) that the orchestrator delegates to. Critical for recreating the multi-agent routing behavior.
Requirements
- Complexity
- Advanced
- Setup time
- ~15 minutes
- Node
- 24+
- Memory
- 512MB
