Get in Touch
 Duration 14 hours

Course Outline

LangGraph and Agent Patterns: A Practical Introduction

  • Graphs versus linear chains: assessing when and why to use them
  • Understanding agents, tools, and planner-executor loops
  • Creating a minimal agentic graph: a foundational workflow example

Managing State, Memory, and Context

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

Implementing Branching Logic and Control Flow

  • Setting up conditional routing and multi-path decision-making
  • Managing retries, timeouts, and circuit breakers
  • Configuring fallbacks, handling dead-ends, and recovery nodes

Leveraging Tools and External Integrations

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

Building Retrieval-Augmented Agent Workflows

  • Strategies for document ingestion and chunking
  • Utilising 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
  • Utilising golden sets, evaluations, and regression tests
  • Monitoring quality, safety, and cost versus latency metrics

Packaging and Deployment

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

Summary and Future Directions

Requirements

  • Practical proficiency in Python
  • Experience in developing LLM applications or prompt chains
  • Understanding of REST APIs and JSON standards

Target Audience

  • AI Engineers
  • Product Managers
  • Developers creating interactive LLM-driven systems

Upcoming Courses

Related Categories