Building Dynamic Workflows with LangGraph and LLM Agents Training Course

LangGraph and Agent Patterns: A Practical Introduction

• Graphs versus linear chains: understanding when and why to use each
• Exploring agents, tools, and planner-executor loops
• Creating a minimal agentic graph: a hello world workflow

Managing State, Memory, and Context

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

Implementing Branching Logic and Control Flow

• Establishing conditional routing and multi-path decision mechanisms
• Applying retries, timeouts, and circuit breaker patterns
• Handling fallbacks, dead-ends, and designing recovery nodes

Utilizing Tools and External Integrations

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

Retrieval-Augmented Agent Workflows

• Strategies for document ingestion and chunking
• Working with embeddings and vector stores using ChromaDB
• Generating grounded responses with citations and safety measures

Evaluation, Debugging, and Observability

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

Packaging and Deployment

• Serving via FastAPI and managing dependencies
• Versioning graphs and implementing rollback strategies
• Developing operational playbooks and incident response protocols

Summary and Future Directions