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.
Course Outline
LangGraph and Agent Patterns: A Practical Primer
- Understanding graphs versus linear chains: when and why to use each.
- Exploring agents, tools, and planner-executor loops.
- Creating a minimal agentic graph with a “Hello workflow” example.
State, Memory, and Context Passing
- Designing graph states and node interfaces.
- Distinguishing between short-term and persisted memory.
- Managing context windows, summarization, and rehydration.
Branching Logic and Control Flow
- Implementing conditional routing and multi-path decisions.
- Handling retries, timeouts, and circuit breakers.
- Utilizing fallbacks, dead-ends, and recovery nodes.
Tool Use and External Integrations
- Invoking functions and tools from nodes and agents.
- Consuming REST APIs and databases within the graph.
- Parsing and validating structured outputs.
Retrieval-Augmented Agent Workflows
- Strategies for document ingestion and chunking.
- Using embeddings and vector stores with ChromaDB.
- Ensuring grounded responses with citations and safeguards.
Evaluation, Debugging, and Observability
- Tracing execution paths and inspecting node interactions.
- Creating golden sets, performing evaluations, and running regression tests.
- Monitoring quality, safety, cost, and latency.
Packaging and Delivery
- Setting up FastAPI serving and managing dependencies.
- Versioning graphs and implementing rollback strategies.
- Developing operational playbooks and incident response plans.
Summary and Next Steps
Requirements
- Proficient working knowledge of Python
- Experience in building LLM applications or prompt chains
- Familiarity with REST APIs and JSON
Target Audience
- AI engineers
- Product managers
- Developers creating interactive LLM-driven systems
14 Hours
