Building Dynamic Workflows with LangGraph and LLM Agents Training Course

LangGraph and Agent Patterns: A Practical Introduction

• Graphs versus linear chains: appropriate use cases and reasoning
• Agents, tools, and planner-executor loops
• Building a basic agentic graph

State, Memory, and Context Management

• Structuring graph state and node interfaces
• Distinguishing between short-term and persisted memory
• Managing context windows, summarisation, and state restoration

Branching Logic and Control Flow

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

Tool Integration and External Connections

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

Retrieval-Augmented Agent Workflows

• Strategies for document ingestion and chunking
• Utilising embeddings and vector stores with ChromaDB
• Generating grounded responses with citations and safety checks

Evaluation, Debugging, and Observability

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

Deployment and Delivery

• Serving via FastAPI and managing dependencies
• Version control for graphs and rollback procedures
• Operational playbooks and incident response protocols

Wrap-up and Next Steps