Intermediate

Developing AI Agents with OpenAI AgentKit

Build, deploy and govern agents with OpenAI AgentKit — Agent Builder, tool calling, guardrails and evals.

Most developers start with a prompt. It works for a simple question, but as soon as a real workflow appears — refunds, approvals, triage — the prompt alone falls apart.

The solution: An agent is like an employee. It stays in the loop, makes decisions step by step, calls tools when needed, and continues until the work is truly done.

Sign in to read this course

A free account unlocks all 514 courses. 20 are readable without one.

What's inside

14 sections
  1. 1 Table of Contents
  2. 2 Introduction — From Prompts to Agents
  3. 3 AgentKit Definition and Core Components
  4. 4 MCP — Model Context Protocol
  5. 5 Building the First Agent with Agent Builder
  6. 6 Tool Calling — Detect → Act → Respond
  7. 7 Deployment — ChatKit vs ChatGPT Apps
  8. 8 Reliability — Tracing, Debugging and Tuning
  9. 9 Guardrails — See, Do, Say
  10. 10 Governance and Security at Scale
  11. 11 Evals — Automated Quality Testing
  12. 12 Reference Tables
  13. 13 Complete Architecture — Diagrams
  14. 14 Conclusion — The Era of AI Operators

Interested in this course?

Contact us to book it or get a custom training plan for your team.