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: timing and rationale
- Agents, tools, and planner-executor loops
- Hello workflow: creating a minimal agentic graph
State, Memory, and Context Transfer
- Designing graph state and node interfaces
- Distinguishing between short-term and persisted memory
- Managing context windows, summarisation, and rehydration
Branching Logic and Control Flow
- Conditional routing and multi-path decision-making
- Implementing retries, timeouts, and circuit breakers
- Handling fallbacks, dead-ends, and recovery nodes
Tool Utilisation and External Integrations
- Executing function/tool calls from nodes and agents
- Consuming REST APIs and databases from the graph
- Parsing and validating structured outputs
Retrieval-Augmented Agent Workflows
- Document ingestion and chunking strategies
- Using embeddings and vector stores with ChromaDB
- Generating grounded responses with citations and safeguards
Evaluation, Debugging, and Observability
- Tracing paths and analysing node interactions
- Utilising golden sets, evaluations, and regression tests
- Monitoring quality, safety, and cost/latency
Packaging and Deployment
- Serving with FastAPI and managing dependencies
- Versioning graphs and implementing rollback strategies
- Operational playbooks and incident response procedures
Summary and Next Steps
Requirements
- Practical proficiency in Python
- Experience developing LLM applications or prompt chains
- Understanding of REST APIs and JSON
Target Audience
- AI Engineers
- Product Managers
- Developers creating interactive LLM-driven systems