Short, practical lessons on how real AI products are built: models, prompting, document search (RAG), agents, evals and shipping. You write real Python in your browser, and you can't move on until you get it.
Implement cosine similarity: the math behind every vector search.
▍Two courses
How it works
Each lesson takes 5–10 minutes. Every step asks you to try something, and you get instant feedback.
One idea, explained simply, with an animation that shows how data moves through the system.
Write Python, put steps in order, play with live widgets, sort and match. You have to get it right to continue.
Hints when you're stuck, explanations when you're right, plus XP and levels to keep you going.
Every lesson ends in something real, like this RAG pipeline:
Know the difference
They overlap, but the daily work is very different. The AI Engineering course trains AI engineers, and teaches enough ML to work well with ML engineers.
Builds reliable systems with deterministic code.
Trains, tunes and serves models from data.
Builds products on top of foundation models.
Curriculum
Switch between the two courses. Open any module to read its lessons and start.
The first module of each course (8 lessons in total) is free. No card, no sign-up. Your progress saves as you go.
Fits a short break. Pick up exactly where you stopped.
Your code runs in real Python inside the page, and hidden tests check it.
Built on how real teams work, and kept up to date.
Enter to continue, ⌘/Ctrl+Enter to check code, Tab to indent.
Get it right and the next step opens automatically. Pause any time.
Free guides
In-depth, plain-English guides to the most-asked questions about AI, each linked to hands-on practice.
Real projects
Every project is a real repository with its tests, README and a one-click ZIP. Push it to GitHub from the page. Finish the AI Engineering course to unlock the capstone — and a free website or app from OrsinAI as your graduation gift.
See all projectsComplete every AI Engineering lesson and every graded step to unlock a free website or app build with OrsinAI.
See all projectsFree tools
AI glossary
keepUp AI is an interactive learning platform with two courses. AI Engineering teaches you to build real AI products with real Python in your browser, labs, quizzes and case studies. Vibe Coding teaches beginners to build, review, debug and launch a real web app with AI coding tools.
Yes. Vibe Coding needs no programming background. For AI Engineering, if you can read basic Python you can start today: every AI idea, from tokens to agents, is taught from zero with plenty of practice.
A beginner course where you plan, build and launch TinyTasks, a responsive web app with Clerk sign-in, a Supabase database with access rules, PostHog analytics and a test-mode payment exercise. It's included in every plan, and the first module is free.
Yes. The first module of each course is completely free (in AI Engineering that's the first 5 lessons), including Keepy the AI tutor, with no card and no sign-up. You can also unlock bonus lessons by inviting friends.
In AI Engineering: LLM features with validated outputs, RAG assistants over your own documents, tool-using agents, MCP servers and eval suites, plus 36 copy-paste templates. In Vibe Coding: a launched first version of your own web app with sign-in, a secure database, analytics and a README.
You can't move on until you've actually done the thing. Every step asks you to write code, review a change, sort, match, solve a quiz or analyze a real case, so the skills stick.
Launch offer
Lifetime access is $69 instead of $139 while we launch, with both courses and every future lesson included. Prefer a subscription? Yearly works out to just $4.08/month.
Lifetime
$139$69one-time
Find out what AI engineers actually do, or start building your first web app with AI in Vibe Coding.
Start lesson 1