Building Dynamic Workflows with LangGraph and LLM Agents Training Course

LangGraph and Agent Patterns: A Practical Introduction

• Comparing graphs vs. linear chains: identifying use cases and benefits
• Exploring agents, tools, and planner-executor architectures
• Building a minimal agentic graph: the "Hello workflow"

State, Memory, and Context Management

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

Branching Logic and Control Flow

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

Tool Utilization and External Integrations

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

Retrieval-Augmented Agent Workflows

• Optimizing document ingestion and chunking strategies
• Utilizing embeddings and vector stores with ChromaDB
• Ensuring grounded responses with citations and safety safeguards

Evaluation, Debugging, and Observability

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

Packaging and Deployment

• Serving via FastAPI and managing dependencies
• Implementing graph versioning and rollback strategies
• Defining operational playbooks and incident response procedures

Summary and Next Steps