Get in Touch
 Duration 35 hours

Course Outline

Advanced LangGraph Architecture

  • Graph topology patterns including nodes, edges, routers, and subgraphs
  • State modeling techniques such as channels, message passing, and persistence
  • Comparisons of DAG versus cyclic flows and hierarchical composition

Performance and Optimization

  • Parallelism and concurrency patterns implemented in Python
  • Strategies for caching, batching, tool calling, and streaming
  • Cost control methods and token budgeting approaches

Reliability Engineering

  • Implementation of retries, timeouts, backoff, and circuit breaking
  • Ensuring idempotency and deduplication of steps
  • Checkpointing and recovery using local or cloud-based stores

Debugging Complex Graphs

  • Techniques for step-through execution and dry runs
  • Inspection of state and tracing of events
  • Reproducing production issues using seeds and fixtures

Observability and Monitoring

  • Structured logging and distributed tracing practices
  • Tracking operational metrics like latency, reliability, and token usage
  • Utilization of dashboards, alerts, and SLO tracking

Deployment and Operations

  • Packaging graphs as services and containers
  • Managing configuration and handling secrets securely
  • Setting up CI/CD pipelines, rollouts, and canary deployments

Quality, Testing, and Safety

  • Development of unit, scenario, and automated evaluation harnesses
  • Implementing guardrails, content filtering, and PII handling
  • Conducting red teaming and chaos experiments to ensure robustness

Summary and Next Steps

Requirements

  • A solid understanding of Python and asynchronous programming
  • Practical experience in developing LLM applications
  • Familiarity with fundamental LangGraph or LangChain concepts

Audience

  • AI platform engineers
  • DevOps professionals specializing in AI
  • ML architects responsible for production LangGraph systems

Number of participants


Price per participant

Upcoming Courses

Related Categories