Grokking Agents in Production

Build, evaluate, and deploy a multi-agent system that actually works. From first principles to a live product on Google Cloud.

6 weeks

self-paced content

Theory + Code

with two instructors

Live on GCP

Not a notebook demo

A COLLABORATION BY

Join our waitlist

to attend our upcoming Masterclass and be among the first to know when we open admissions for our upcoming course, and receive a special early bird discount.

A 6-week course where you'll build a real multi-agent PDF analyzer, learning the theory and engineering behind RAG, ReAct, multi-agent architectures, MCP, A2A, and agent evaluation along the way.

First Name

Last Name

Country

Comment or question (optional)

After signing up you will receive invitations to upcoming programs and helpful resources. You can unsubscribe anytime.

During the course you will learn:

Build a production-grade multi-agent system, not a demo, a real system deployed on Google Cloud.
Understand why naive RAG breaks and how to fix the parts that silently ruin your results
Master the ReAct pattern, and go from static LLM calls to agents that actually reason and act.
Design multi-agent architectures supervisor, hierarchical, swarm, and when to use each
Work with MCP and A2A the two protocols becoming the backbone of the agent ecosystem.
Evaluate your agents properly with RAG metrics, trajectory evaluation, and LLM-as-judge.
Deploy as real services containerization, Cloud Run, CI/CD, monitoring, and cost

Miguel Otero Pedrido

Senior ML Engineer, physicist, and creator of the hugely popular Neural Maze blog and YouTube channel, Miguel has helped thousands of students learn how to build and ship real AI systems. He specializes in the part most courses skip: real infrastructure, real deployment, and real users. In this course, he owns the engineering: translating theory into working systems running on Google Cloud.

Luis Serrano

AI educator, mathematician, and founder of Serrano Academy, Luis has helped thousands of students around the world make sense of complex AI concepts through his popular courses, Grokking Machine Learning book, and YouTube channel. With a background at Google, Apple, and Cohere, he covers machine learning, NLP, deep learning, and quantum computing. In this course, he owns the theory: the intuition and mental models behind every concept you'll build.