Model Online / On-Site
Duration
Modules 5 modules

Course Objective & Scope

Once agents leave the demo stage, the real challenge is managing business state consistently beyond chat history: which step finished, what data was collected, where to resume if the process is interrupted. This course teaches you to model state as an explicit schema and design the workflow as a controllable graph.

LangGraph StateGraph, reducers, checkpointers and threads are covered alongside the role of workflow engines such as Temporal. Participants model one of the organisation's approval or application processes as a stateful agent workflow that can resume after interruption.

Who Should Attend?

  • Software engineers developing multi-step agent workflows
  • Solution architects integrating agents into existing business processes
  • Platform engineers responsible for agent infrastructure
  • Prerequisite: Python and basic LLM API experience

Key Takeaways

  • Model agent state with a typed schema and reducers
  • Build flows that resume where they left off using checkpoints
  • Isolate state per thread and session
  • Strike the right balance between a free-form agent loop and a deterministic workflow
  • Reproduce and fix bugs by inspecting state history

Curriculum

From Chat History to Business State
  • The difference between a message list and structured state
  • State schema design: TypedDict and Pydantic
Workflows as Graphs
  • Nodes, edges and conditional edges
  • The state machine approach and transition rules
  • Merging parallel updates with reducers
Checkpoints and Persistence
  • SQLite and PostgreSQL checkpointers
  • Threads, sessions and state isolation
  • Time travel: returning to and replaying past state
Integrating Workflow Engines
  • The role of durable workflow engines such as Temporal
  • Separating agent logic from process orchestration
Business Process Modelling Workshop
  • Turning a real approval process into a stateful agent
  • Testing interruption and restart scenarios

Other Courses in This Category

  • Tool Design and Tool Contracts for LLM Agents

    Hands-on course on designing tools agents can use reliably: naming, descriptions, JSON Schema parameters, error messages, tool contracts, versioning and permission scopes.

    AI Agent Engineering Corporate
    Live Course
    5 modules
    View
  • Building Agent Systems with LangGraph

    Hands-on technical course on building production-ready agent systems with LangGraph: StateGraph, conditional edges, checkpointers, interrupt-based human-in-the-loop, subgraphs and the Send API.

    AI Agent Engineering Corporate
    Live Course
    6 modules
    View
  • OpenAI Agents SDK and Tool-Based Agent Systems

    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.

    AI Agent Engineering Corporate
    Live Course
    5 modules
    View
  • Building MCP Servers and Clients (Model Context Protocol)

    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.

    AI Agent Engineering Corporate
    Live Course
    5 modules
    View
  • Multi-Agent Orchestration: Supervisor, Hierarchical and Swarm Patterns

    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.

    AI Agent Engineering Corporate
    Live Course
    5 modules
    View
  • Agent Memory: Short-Term and Long-Term Memory Architectures

    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.

    AI Agent Engineering Corporate
    Live Course
    5 modules
    View

Get in touch