1. Home
  2. Workshops
  3. Building Agents with the OpenAI Agents SDK

Building Agents with the OpenAI Agents SDK

In this two-day workshop your developers build agents with the OpenAI Agents SDK. You learn the core concepts, create agents that use tools and hand work to each other, add guardrails and tracing, and test the behaviour systematically. By the end you have a working agent for a use case from your own context, with defined limits and approval steps.

Request without obligation

Deutsche Version

Duration
2 days
Level
Advanced
Format
Remote or on-site, English or German
Group size
Up to 12 participants per trainer

Who it is for

  • Software engineers building agent-based features
  • Teams automating internal workflows with agents
  • Architects comparing agent frameworks

What your team will be able to do

  • Build and run an agent with the SDK and explain how it works
  • Define tools and control which actions an agent may take
  • Design handoffs between specialised agents
  • Apply guardrails and input and output checks
  • Use tracing to debug and evaluate behaviour
  • Plan human approval for sensitive actions

Agenda

  1. Concepts and first agentAgents, tools, runs and the project structure. A first working agent by the end of the session.
  2. Tools and structured outputDefining function tools with validated inputs and returning structured results.
  3. Handoffs and orchestrationSplitting responsibilities between agents and routing work between them.
  4. GuardrailsValidating inputs and outputs, handling untrusted content and limiting what an agent can do.
  5. Tracing and evaluationInspecting runs, building test cases and comparing behaviour across changes.
  6. Human in the loopApproval steps for risky actions and designing clear escalation paths.
  7. CapstoneParticipants present an agent for a real use case and review its risks and next steps.

Prerequisites

  • Programming experience in Python or TypeScript
  • Experience with LLM APIs
  • API access prepared before day one

Why apprat.io workshops

  • Taught by practising AI Code Engineers
  • Your repositories or a sandbox project
  • AI speed, human responsibility: review, security and governance included
  • ISO 9001 & ISO/IEC 27001 certified processes
  • Follow-up office hours after 30 days

Request without obligation

Tell us about your team and goals. We reply within one business day with a tailored agenda and a quote – free and without obligation.

24/7 call support in English & German:
+49 761 519 751 50

Frequently asked questions

Do we need to know the SDK beforehand?

No. We introduce it from the basics, but programming and API experience are required.

Can we use models from other providers?

This depends on what the SDK supports. We clarify your requirements before the workshop.

What about data protection?

We discuss data flows and settings in general terms and recommend involving your data protection officer. This is not legal advice.

Fields marked * are required.

Related workshops

All workshops