Building Dynamic Workflows with LangGraph and LLM Agents Training Course

LangGraph and Agent Patterns: A Practical Introduction

• Graphs versus linear chains: When to use them and why
• Agents, tools, and planner-executor loops
• Minimal agentic graph example

State, Memory, and Context Transfer

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

Branching Logic and Control Flow

• Conditional routing and multi-path decision-making
• Implementing retries, timeouts, and circuit breakers
• Handling fallbacks, dead-ends, and recovery nodes

Tool Usage and External Integrations

• Function/tool calling from nodes and agents
• Utilizing REST APIs and databases within the graph
• Parsing and validating structured outputs

Retrieval-Augmented Agent Workflows

• Strategies for document ingestion and chunking
• Using embeddings and vector stores with ChromaDB
• Generating grounded responses with citations and safeguards

Evaluation, Debugging, and Observability

• Tracing paths and examining node interactions
• Establishing golden sets, evaluations, and regression tests
• 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 plans

Overview and Future Directions