Building Dynamic Workflows with LangGraph and LLM Agents Training Course

LangGraph and Agent Patterns: A Practical Introduction

• Graphs versus linear chains: understanding the appropriate use cases
• Agents, tools, and the planner-executor loop architecture
• Creating a minimal agentic graph: a "Hello workflow" example

State, Memory, and Context Management

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

Branching Logic and Control Flow

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

Tool Usage and External Integrations

• Executing function and tool calls from nodes and agents
• Interacting with REST APIs and databases within 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 safeguards

Evaluation, Debugging, and Observability

• Tracing execution paths and analyzing node interactions
• Creating golden sets, evaluations, and regression tests
• Monitoring quality, safety, cost, and latency

Packaging and Deployment

• Serving applications with FastAPI and managing dependencies
• Versioning graphs and establishing rollback strategies
• Developing operational playbooks and incident response plans

Summary and Future Directions