AI engineering: Agents

AI engineering: Agents
In this course you'll learn to work with reasoning models to build production-grade AI agents that can autonomously tackle complex workflows, from deep analysis to support agents. Learn to architect and evaluate robust systems that combine LLMs, tools, memory, and planning to ship real-world applications.
2 Hours
Free

Learnings & outcomes

  • Design reliable agent architectures combining tool integration, memory systems, and autonomous workflows
  • Master multi-agent collaboration through orchestrator-worker patterns and structured hand-offs
  • Evaluate agent performance across accuracy, latency, and cost using reproducible benchmarking methods

Curriculum

  • Deterministic LLM workflows – chaining, structure, and reliability
  • Single-agent systems – autonomous decision taking
  • Context, memory and retrieval – giving agents a real memory
  • Multi-agent collaboration – building teams of LLM agents
  • Evaluation and Benchmarking – measuring, improving & trusting Agents
  • MCPs
In partnership with
In partnership with
Course Instructors:

Ilan Bigio

OpenAI
Developer Experience Engineer
Ilan graduated from Brown University, spent three years at Google, and is currently working at OpenAI. He has a passion for teaching and learning and spends an astounding amount of time on his pet projects.

Anish Shah

Weights & Biases
AI Engineer
Anish loves turning ML ideas into ML products. Anish started his career working with multiple Data Science teams within SAP, working with traditional ML, deep learning, and recommendation systems before landing at Weights & Biases. With the art of programming and a little bit of magic, Anish crafts ML projects to help better serve our customers, turning “oh nos” to “a-ha”s!
Explore our other courses