Agent Patterns
AI systems that choose their own steps dynamically
Routing & Classification
Intelligent routing and request classification
Orchestration & Sub-Agents
Coordinating multiple specialized agents
Human-in-the-Loop
Human approval and oversight workflows
Evaluation & Optimization
Quality assessment and iterative improvement
Multi-Step & Parallel
Complex multi-step and parallel execution patterns
All Agent Patterns Patterns
Agent Routing Pattern
Route user queries to specialized AI agents based on context and intent. Includes dynamic agent selection, load balancing, and fallback handling.
Orchestrator-Worker Pattern
Coordinate multiple worker agents for project management. Handles task distribution, progress tracking, and result synthesis.
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.
Human in the Loop Plan Builder Agent
Uses ToolLoopAgent pattern to gather requirements and generate plans. Generates markdown plans with structured todo lists.
HIL Inquire Multiple Choice
Gather information through AI-driven multiple choice questions. Includes approval workflows and real-time rendering.
HIL Inquire Text Input
Gather detailed information through AI-driven text input questions. Includes approval workflows and real-time rendering.
Evaluator-Optimizer Pattern
Improve output quality with dual agents. Evaluator analyzes quality while optimizer refines results through iterative feedback.
