Agent Routing Pattern
Route user queries to specialized AI agents based on context and intent. Includes dynamic agent selection, load balancing, and fallback handling.
View Full Pattern on Desktop
Problems Solved
- Route user queries to specialized AI agents based on context and intent
- Dynamic agent selection via generateObject classification
- Model selection based on query complexity (simple vs complex)
- Streaming responses with custom data parts for classification metadata
- 7 specialized agent configs (general, product, technical, sales, billing, etc.)
- Load balancing and fallback handling across multiple providers
Use Cases
- Customer service request routing
- Technical support ticket classification
- Sales inquiry qualification
- Multi-department request handling
- Intent-based agent orchestration
- Support desk automation
AI SDK APIs
Tags
Requirements
- Node.js
- 24+
- Memory
- 512MB
- Other
- OpenAI API key
- Perplexity API key (optional)
- Deepseek API key (optional)
External Services
Ready to use?
View the full interactive pattern with live preview and copy the source code.
Open Live PreviewView Pattern on DesktopRelated Patterns
Multi-Step Tool Pattern
Execute multi-step workflows with typed tools. Includes streaming, tool chaining, and decision-making for automated tasks.
HIL Inquire Text Input
Gather detailed information through AI-driven text input questions. Includes approval workflows and real-time rendering.
Human in the Loop Plan Builder Agent
Uses ToolLoopAgent pattern to gather requirements and generate plans. Generates markdown plans with structured todo lists.
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.