Hugo & Stefan

Cohort 1

Cohort 5

Cohort 4

Cohort 3

Cohort 2

Building agents means making sense of harnesses, context engineering, and the pressure to rebuild every time a new model drops. The best writing on what actually works is scattered across blog posts, podcasts, and livestreams. This is the reading list I share with builders who want to cut through it. Hands-on builds you can do in an hour. Deeper conversations on harness and context engineering. Agentic search. Evals. The canonical posts worth your time.

Building Effective Agent Harnesses

This is Chapter 1 of our 300-page course reader: yours free. The full reader spans 9 chapters covering the whole AI software development lifecycle, including evaluation, testing, RAG, agents, multimodal systems, and fine-tuning. It's the companion to our live course, taught by Hugo Bowne-Anderson and Stefan Krawczyk, with guest perspectives from practitioners at Google DeepMind, Pydantic, Chroma, and more. In this chapter, you'll learn why most AI projects stall after the demo: and the evaluation-driven development framework that gets them to prod.

Building AI Applications: The Reader

Want to build LLM-powered applications but not sure where to start? This handpicked guide features the best resources on Python fundamentals, LLM evaluation, AI agent design, and scaling generative AI systems. Learn from experts like Chip Huyen, Hamel Husain, Shreya Shankar, and Sebastian Raschka to accelerate your LLM development workflow and avoid common pitfalls. Whether you’re an engineer, researcher, or founder, this guide will help you build more reliable and production-ready AI systems.

🚀 Essential LLM & AI Engineering Resources: A Curated Guide for Engineers & Data Scientists

Want to build smarter AI agents? This handpicked guide features the best resources on AI agent design, planning, tool use, and failure modes. Learn from industry leaders like Anthropic, Chip Huyen, and Hugging Face to level up your LLM-powered agents and avoid common pitfalls. Whether you’re an engineer, researcher, or founder, this guide will help you build more reliable and capable AI agents.

Master AI Agents: A Handpicked Guide to the Best Resources

Engineers and engineering leaders who build, deploy, and scale software systems.

Data scientists who apply statistical and ML techniques to extract insights from data.

Applying AI tools and techniques to professional workflows — assign alongside more specific AI topics.

Building autonomous AI agent systems that take actions, use tools, and orchestrate multi-step workflows.

Build AI-powered software reliably & from first principles. Learn the GenAI software development lifecycle: agents, evals, iteration & more

AI Builder/Educator (6 Million Students)

Hugo Bowne-Anderson

AI & data engineer, consultant, educator of 6+ million students (ex-Yale)

AI Builder with 15 years of experience

Stefan Krawczyk

Agentforce; Ex-Stitch Fix; 13+ Years building / productionizing data, ML, Agents

Building AI Applications for Data Scientists and Software Engineers

Data Analyst

AI Leader

Data Manager

Enteprise Data Architect

Clinician Data Scientist

Student

Gen AI intern

DS & ML Mentor & Content Creator

AI ML Customer Engineer

We recently finished our final cohort and are now cooking up something new. <a target="_blank" rel="noopener noreferrer nofollow" href="https://tally.so/r/EkLjyA">To hear about it (and help shape what we build), drop your thoughts here</a>.If you’re a software engineer or data scientist, chances are you’ve built an impressive proof of concept (POC) that showcases the potential of LLMs.But these POCs often fail to scale into reliable, production-ready applications. The result? Endless iteration cycles, unreliable outputs, and frustration as teams struggle in what we call “POC purgatory.”It doesn’t have to be this way.With the right principles, processes, &amp; workflows, you can build LLM applications that work in production, without overcomplicating pipelines or chasing trends. This course focuses on the iterative development, evaluation, and debugging practices that make AI systems production-ready.You'll build with state-of-the-art tools like RAG, fine-tuning, MCP, context engineering, and agents, but the emphasis is on building scalable, robust systems, ensuring you leave with the mindset and skills to adapt as the technology evolves.Learn how to design, test, &amp; deploy generative AI applications, and iterate rapidly.

Master the patterns and processes that underpin successful GenAI app development

Move beyond POCs and build production-ready AI systems

Build State-Of-The-Art AI Agents

Accelerate your development process with best-in-class "Evals" & LLMs Judges

Develop hands-on expertise by building GenAI and LLM apps

Showcase Tangible Results

Data scientists, machine learning engineers who are sick &amp; tired of seeing and building prototypes &amp; want to ship reliable LLM applications

Software engineers who want to learn how to build Generative AI systems and learn the LLM software development lifecycle.

Learn directly from Hugo & Stefan

Hugo & Stefan

Courses

Building AI Applications for Data Scientists and Software Engineers

Lightning Lessons

The Agentic Lifecycle with Opik: Trace, Evaluate, Iterate

How To Build Your First Agentic Search Application

Ship AI-Generated Code You Actually Understand

Making Sense of Millions of Conversations for AI Agents

Making LLM Agents Observable & Debuggable

Don't Tweak Prompts. Engineer Agents.

Resources

Building Effective Agent Harnesses

Building AI Applications: The Reader

🚀 Essential LLM & AI Engineering Resources: A Curated Guide for Engineers & Data Scientists

Master AI Agents: A Handpicked Guide to the Best Resources