Course · 9 chapters
Frameworks d'agents
Build production multi-agent systems with the OpenAI Agents SDK and Claude Agent SDK, the engine behind Claude Code. 9 chapters for working engineers.
What you'll be able to do
- Master the OpenAI and Anthropic APIs
- Build multi-agent systems with the OpenAI SDK
- Ship autonomous agents with the Claude Agent SDK
- Add guardrails, handoffs, and tracing
- Test non-deterministic agents in CI
- Compare LangGraph, CrewAI, and AutoGen
What's inside
- 1Agent Frameworks : Par Ici
Une orientation de 12 minutes au parcours de compétences Agent Frameworks — pourquoi il existe, ce que tu pourras faire, comment les chapitres se relient, et où commencer.
- 2Agent Frameworks : le paysage
Navigue la pile API-vers-agent chez OpenAI et Anthropic — comprends les couches avant de construire.
- 3Maîtrise de l'API OpenAI
Maîtrise l'API Responses et Chat Completions — comprends quand utiliser chacune et comment migrer.
- 4API & SDK Anthropic
Maîtrise l'API Messages, l'utilisation d'outils, la réflexion étendue et le cache de prompts — construis avec Claude depuis les fondamentaux.
- 5OpenAI Agents SDK
Construis des systèmes multi-agents avec garde-fous, transferts et traçage — le framework d'OpenAI pour l'IA autonome.
- 6Claude Agent SDK
Construis des agents autonomes avec le framework d'Anthropic — le moteur qui propulse Claude Code, sous forme de bibliothèque que tu contrôles.
- 7Workflows d'agents en production
Déploie des systèmes multi-agents qui s'intègrent à de vrais outils, scalent dans des conteneurs et vérifient leur propre travail.
- 8Test et Evaluation des Agents
Livre des agents que tu peux verifier — mock les outils, trace les decisions, construis des golden datasets et conditionne les deploiements aux resultats d'eval.
- 9LangGraph et les agents multi-frameworks
Lire, déboguer et livrer sur LangGraph, CrewAI et AutoGen — les trois frameworks que tu croiseras dans le code des clients.
Frequently asked questions
- What will I be able to build after this Agent Frameworks course?
- You go from raw API calls to production multi-agent systems. You build directly with the OpenAI Agents SDK and the Claude Agent SDK (the engine behind Claude Code), wire in tool use, multi-agent handoffs and guardrails, test agents in CI/CD, deploy production workflows, and learn to read and debug the LangGraph, CrewAI, and AutoGen frameworks you encounter in real customer code.
- Who is this course for?
- It is built for software engineers at a practitioner level who want to build, test, and ship AI agents. It suits backend, full-stack, and AI engineers moving from raw API calls to production agent systems.
- Do I need coding experience to take this course?
- Yes. This is a practitioner-level engineering path that has you working directly with the OpenAI and Anthropic SDKs, so you should be comfortable reading and writing code before starting.
- How long is the course and is there a certificate?
- The path has 9 chapters, including a Start Here orientation, the landscape of agent frameworks, the OpenAI and Anthropic APIs and SDKs, production workflows, testing and evaluation, and multi-framework agents. You earn a certificate of completion when you finish the path.
- Which agent frameworks does the course cover?
- It covers the OpenAI Agents SDK and Anthropic's Claude Agent SDK in depth, plus the OpenAI Responses API, the Anthropic Messages API, and reading and debugging agents built with LangGraph, CrewAI, and AutoGen.
Earn a certificate
Complete all chapters to receive your certificate of completion.