Building Dynamic Workflows with LangGraph and LLM Agents Training Course

LangGraph and Agent Patterns: A Practical Introduction

• Graphs versus linear chains: determining when and why to use them
• Understanding agents, tools, and planner-executor loops
• Building a basic agentic graph: a starting point

Managing State, Memory, and Context

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

Branching Logic and Control Flow

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

Tool Utilization and External Integrations

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

Retrieval-Augmented Agent Workflows

• Strategies for document ingestion and chunking
• Using embeddings and vector stores with ChromaDB
• Generating grounded responses with citations and safeguards

Evaluation, Debugging, and Observability

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

Packaging and Deployment

• Serving via FastAPI and managing dependencies
• Versioning graphs and implementing rollback strategies
• Operational playbooks and incident response procedures

Conclusion and Future Directions