Course Objective & Scope
LangGraph is one of the most widely used open-source frameworks for modelling agents as explicit state graphs, giving teams control, persistence and observability. The course moves from a simple tool-calling agent to a system with persistent memory, approval steps and sub-agents that share the work.
Labs cover StateGraph, prebuilt agents, checkpointers, human-in-the-loop with interrupt(), subgraphs, streaming and tracing with LangSmith. The programme is adapted to the organisation's technology stack; the output is a tested LangGraph application running on an organisational scenario.
Who Should Attend?
- Software developers building LLM applications in Python
- AI engineers who want to take agent prototypes to production
- Teams using LangChain who need more control
- Prerequisite: Python, async programming and LLM API basics
Key Takeaways
- Build agent graphs from state, nodes and edges with LangGraph
- Develop persistent, resumable agents with checkpointers
- Add approval and edit steps with interrupt
- Design multi-agent and parallel flows with subgraphs and the Send API
- Monitor and debug agent behaviour with LangSmith tracing
Curriculum
LangGraph Core Concepts
- StateGraph, nodes, edges and conditional edges
- Prebuilt ReAct agent versus a custom graph
Tools, Streaming and Structured Output
- ToolNode and tool calling integration
- Token and event streaming
- Reliable intermediate results with structured output
Persistence and Memory
- Checkpointers, threads and time travel
- Long-term memory with the Store
Human-in-the-Loop
- Approve, edit and reject flows with interrupt() and Command
- Pausing sensitive tool calls
Subgraphs and Multi-Agent
- Supervisor and handoff patterns
- Map-reduce style parallel work with the Send API
Deployment and Observability
- Tracing and evals with LangSmith
- Serving the agent as an API and a testing strategy
Other Courses in This Category
-
Course on building tool-based agents with the OpenAI Agents SDK and Responses API: function tools, hosted tools such as web search and file search, handoffs, guardrails, sessions and built-in tracing.
- Live Course
- 5 modules
-
Hands-on course on building Model Context Protocol servers that expose tools, resources and prompts, and clients that consume them: stdio and Streamable HTTP, OAuth-based authorisation, security and testing.
- Live Course
- 5 modules
-
Designing multi-agent systems with supervisor, hierarchical, orchestrator-worker and swarm patterns: context isolation, task routing, cost control and a comparison of LangGraph, CrewAI and Microsoft Agent Framework.
- Live Course
- 5 modules
-
Hands-on training on designing working, episodic, semantic and procedural memory layers for AI agents using context summarisation, vector and graph memory stores, memory consolidation and retention policies.
- Live Course
- 5 modules
-
Technical course on safely executing LLM- and agent-generated code using gVisor, Firecracker microVMs, container isolation, network/filesystem restrictions and resource quotas.
- Live Course
- 5 modules
-
Course on evaluating end-to-end task completion, trajectory quality and tool selection in AI agents, and setting up distributed tracing and live monitoring with OpenTelemetry, LangSmith, Arize Phoenix and Langfuse.
- Live Course
- 5 modules
Get in touch
