Building Dynamic Workflows with LangGraph and LLM Agents Training Course

LangGraph and Agent Patterns: A Practical Introduction

• Graphs versus linear chains: determining the appropriate use cases
• Exploring agents, tools, and planner-executor loops
• Basic workflow: implementing a minimal agentic graph

State, Memory, and Context Management

• Defining graph state and node interfaces
• Distinguishing between short-term and persisted memory
• Handling context windows, summarization, and data rehydration

Branching Logic and Control Flow

• Implementing conditional routing and multi-path decision-making
• Managing retries, timeouts, and circuit breakers
• Designing fallbacks, handling dead-ends, and creating recovery nodes

Tool Utilization and External Integrations

• Executing function and tool calls from nodes and agents
• Accessing REST APIs and databases through the graph structure
• Parsing and validating structured outputs

Retrieval-Augmented Agent Workflows

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

Evaluation, Debugging, and Observability

• Tracing execution paths and examining node interactions
• Using golden sets, evaluations, and regression testing
• Monitoring quality, safety, and cost/latency metrics

Packaging and Deployment

• Serving applications via FastAPI and managing dependencies
• Version control for graphs and implementing rollback strategies
• Establishing operational playbooks and incident response protocols

Recap and Future Directions