Building Dynamic Workflows with LangGraph and LLM Agents Training Course

LangGraph and Agent Patterns: A Practical Introduction

• Graphs vs. linear chains: applicable scenarios and rationale
• Agents, tools, and planner-executor cycles
• Hello workflow: building a minimal agentic graph

State, Memory, and Context Management

• Defining graph state and node interfaces
• Distinguishing between short-term and 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

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

Retrieval-Augmented Agent Workflows

• Document ingestion and chunking methodologies
• Utilizing embeddings and vector stores with ChromaDB
• Generating grounded responses with citations and safeguards

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

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

Wrap-up and Future Directions