Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
LangGraph and Agent Patterns: A Practical Introduction
- Graphs versus linear chains: strategic timing and rationale
- Core concepts of agents, tools, and planner-executor loops
- Foundational workflows: building a minimal agentic graph
State Management, Memory, and Context Propagation
- Defining graph states and node interface standards
- Distinguishing between short-term memory and persisted memory
- Managing context windows, implementing summarization, and rehydrating states
Advanced Branching Logic and Control Flow
- Implementing conditional routing and multi-path decision making
- Configuring retries, timeouts, and circuit breaker patterns
- Handling fallbacks, dead-ends, and recovery nodes
Tool Integration and External Systems
- Executing function and tool calls from nodes and agents
- Interacting with REST APIs and databases from within the graph
- Parsing and validating structured outputs
Retrieval-Augmented Agent Workflows
- Strategies for document ingestion and chunking
- Utilizing embeddings and vector stores with ChromaDB
- Generating grounded responses with citations and safety safeguards
Evaluation, Debugging, and Observability
- Tracing execution paths and analyzing node interactions
- Establishing golden sets, evaluations, and regression testing frameworks
- Monitoring quality, safety, cost efficiency, and latency metrics
Deployment and Operational Packaging
- Serving applications via FastAPI and managing dependencies
- Versioning graphs and defining rollback strategies
- Developing operational playbooks and incident response protocols
Summary and Future Directions
Requirements
- Solid proficiency in Python
- Practical experience in developing LLM applications or constructing prompt chains
- Comfort with REST API interactions and JSON data structures
Target Audience
- AI Engineers
- Product Managers
- Developers specializing in interactive LLM-driven systems