Skip to content

Building with AI

The practitioner track — how to actually build useful AI products. This is where our courses go deep.

A powerful AI model is like a professional kitchen oven: amazing on its own, but an oven doesn't hand you dinner. Building with AI is everything that turns that raw power into a meal someone actually wants to eat. You write clear instructions so the model knows what to make (this is prompting). You give it the right ingredients — your own documents and data — so its answers fit your situation. You taste-test constantly, checking that the results are correct before serving them. And you make sure the whole kitchen runs fast, cheaply, and safely, even when thousands of orders arrive at once. It's less about inventing the oven and more about running a great restaurant around it: reliable, repeatable, and trustworthy.

The main ideas

  • Prompt engineering — Reliable prompting patterns for real applications.
  • Building RAG systems — Chunking, embeddings, retrieval, and grounding end to end.
  • Building agents — Tools, memory, control loops, and evaluation for agentic apps.
  • Fine-tuning & evals — When to fine-tune, and how to build evals you trust.
  • Shipping to production — Cost, latency, safety, and deploying on the edge.

NLP & Large Language Models · AI Agents & Autonomy · Data & MLOps · Applications & Industry

Want to make things?

Head to AI School — AI camps where kids build their own games.