Building Dynamic Workflows with LangGraph and LLM Agents Training Course

LangGraph and Agent Patterns: A Practical Introduction

• Comparing graphs and linear chains: timing and rationale
• Agents, tools, and planner-executor loops
• Hello workflow: building a minimal agentic graph

State, Memory, and Context Management

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

Branching Logic and Control Flow

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

Tool Usage and External Integrations

• Invoking functions and tools from nodes and agents
• Interacting with REST APIs and databases via the graph
• Parsing and validating structured outputs

Retrieval-Augmented Agent Workflows

• Document ingestion and chunking techniques
• Utilizing embeddings and vector stores with ChromaDB
• Generating grounded responses with citations and safety measures

Evaluation, Debugging, and Observability

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

Packaging and Deployment

• FastAPI integration and dependency management
• Graph versioning and rollback strategies
• Operational playbooks and incident response procedures

Summary and Future Directions