Building Dynamic Workflows with LangGraph and LLM Agents Training Course

LangGraph and Agent Patterns: A Practical Introduction

• Comparing graphs and linear chains: determining when and why to use each
• Understanding agents, tools, and the planner-executor loop pattern
• Building a 'Hello Workflow': a minimal example of an agentic graph

Managing State, Memory, and Context

• Structuring graph state and defining node interfaces
• Distinguishing between short-term memory and long-term persisted storage
• Managing context windows, data summarization, and state rehydration

Advanced Branching Logic and Control Flow

• Implementing conditional routing and managing multi-path decision points
• Configuring retries, timeout handling, and circuit breaker patterns
• Handling fallbacks, dead-ends, and implementing recovery nodes

Tool Utilization and External System Integration

• Executing function and tool calls from graph nodes and agents
• Interacting with REST APIs and databases directly from the graph
• Parsing and validating structured outputs effectively

Retrieval-Augmented Agent Workflows

• Strategies for document ingestion and data chunking
• Utilizing embeddings and vector stores with ChromaDB
• Generating grounded responses with proper citations and safety safeguards

Evaluation, Debugging, and System Observability

• Tracing execution paths and analyzing node interactions
• Creating golden datasets, running evaluations, and performing regression testing
• Monitoring quality metrics, safety parameters, and cost/latency performance

Packaging and Deployment Strategies

• Serving applications via FastAPI and managing dependencies
• Versioning graph structures and implementing rollback strategies
• Developing operational playbooks and incident response procedures

Course Summary and Recommended Next Steps