Building Dynamic Workflows with LangGraph and LLM Agents Training Course

LangGraph and Agent Patterns: A Practical Introduction

• Graphs versus linear chains: Identifying when and why to use each
• Agents, tools, and the planner-executor loop
• Hello workflow: Building a minimal agentic graph

State Management, Memory, and Context Transfer

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

Branching Logic and Control Flow

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

Tool Utilization and External Integrations

• Invoking functions and tools from nodes and agents
• Connecting the graph to REST APIs and databases
• Parsing and validating structured outputs

Retrieval-Augmented Agent Workflows

• Document ingestion and optimal chunking strategies
• Leveraging embeddings and vector stores with ChromaDB
• Generating grounded responses with citations and safety measures

Evaluation, Debugging, and Observability

• Tracing execution paths and inspecting node interactions
• Utilizing golden sets, evaluations, and regression testing
• Monitoring quality, safety, cost, and latency

Packaging and Deployment

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

Conclusion and Future Directions