Building Dynamic Workflows with LangGraph and LLM Agents Training Course

LangGraph and Agent Patterns: A Practical Introduction

• Graphs versus linear chains: applicability and rationale.
• Agents, tools, and planner-executor loops.
• Basic workflow: constructing a minimal agentic graph.

State, Memory, and Context Propagation

• Structuring graph state and node interfaces.
• Differentiating short-term memory from persisted memory.
• Managing context windows, summarization, and state restoration.

Branching Logic and Control Flow

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

Tool Usage and External Integrations

• Executing function and tool calls from nodes and agents.
• Accessing REST APIs and databases within the graph structure.
• 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 safety measures.

Evaluation, Debugging, and Observability

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

Packaging and Deployment

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

Summary and Future Directions