Model Online / On-Site
Duration
Modules 5 modules

Course Objective & Scope

The OpenAI Agents SDK is a lightweight framework that expresses agents, tools, handoffs and guardrails with a small set of primitives. This course shows how to build tool-using agents for business tasks with this SDK on top of the Responses API, and how to keep them under control in production.

Labs cover function tools, hosted tools (web search, file search, code interpreter), MCP server connections, handoffs between agents, input/output guardrails, session-based memory and tracing. Participants build a customer support or internal operations assistant made of several specialist agents, based on an organisational scenario.

Who Should Attend?

  • Software developers building applications on the OpenAI platform
  • AI engineers creating tool-using assistants
  • Technical leads selecting an agent framework
  • Prerequisite: Python or TypeScript and basic LLM API experience

Key Takeaways

  • Set up agents, tools and the Runner with the Agents SDK
  • Combine function tools with hosted tools
  • Design task handoffs between specialist agents
  • Validate inputs and outputs with guardrails
  • Monitor and evaluate agent runs with tracing

Curriculum

Introduction to the Responses API and Agents SDK
  • Agent, Runner and the run loop
  • Instructions, model selection and structured output
Tools
  • Defining function tools and type validation
  • Web search, file search and code interpreter
  • Connecting MCP servers to an agent
Handoffs and Agent-as-Tool
  • Triage agent and specialist agents
  • The difference between a handoff and using an agent as a tool
Guardrails and Sessions
  • Input and output guardrails, tripwires
  • Conversation memory with sessions
Tracing and Applied Project
  • Built-in tracing and external observability tools
  • End-to-end development of a multi-agent support assistant

Other Courses in This Category

  • 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
  • Sandboxing and Secure Code Execution for AI Agents

    Technical course on safely executing LLM- and agent-generated code using gVisor, Firecracker microVMs, container isolation, network/filesystem restrictions and resource quotas.

    AI Agent Engineering Corporate
    Live Course
    5 modules
    View
  • Agent Evaluation, Tracing and Production Monitoring

    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.

    AI Agent Engineering Corporate
    Live Course
    5 modules
    View
  • Resilience, Error Recovery and Durable Execution in Agent Systems

    Training on protecting multi-step agents against API outages, rate limits, partial failures and crashes using retries, model fallbacks, idempotency, compensating actions and durable execution with Temporal and LangGraph.

    AI Agent Engineering Corporate
    Live Course
    5 modules
    View

Get in touch