AI Engineering line, station 1 of 6
Vibe Coding: Build Apps with AI
Build and ship a real app by describing it to AI coding tools, and learn enough to review, fix and secure what they write.
- 6lessons
- 3.5 hto read and do
- Beginnerlevel
- 6podcast episodes
- 5checked exercises
Tools you'll use in this course
The lessons open these with a template ready. They work for your own job too, no course needed.
About this course
AI coding tools can now build a working app from a good description. The people who get real value from them know how to describe what they want, how to steer the tool in small steps, and how to check that the result is correct and safe. This course teaches exactly that, for people with little or no coding experience and for developers who want to work this way.
You build a small reorder app for Ravi, who runs a corner shop that buys its stock from Mangrove Market, the fictional grocery chain used across Kolom. Today he phones in the same order every week. Your app remembers his usual order, lets him change it and send it in three taps, and shows his past orders. You choose an AI tool, write a one-page spec the AI can follow, build in small steps with a Git save point after each one, read and fix what the AI wrote, set up the database with sign-in and row-level access rules so one shop never sees another's orders, keep secret keys out of the code, deploy it, watch it, and decide when it is time to hand it to an engineer.
You don't need to know how to code. You will learn to read code well enough to question it, and small auto-checked exercises in your browser let you practise exactly that. Every lesson has a podcast episode too.
What you will be able to do
- Choose between app builders, AI code editors and coding agents for the job in front of you
- Write a one-page spec with users, screens, data, rules and acceptance checks that an AI tool can follow
- Build an app in small steps with an AI assistant, checking and committing each step
- Read and question AI-written code, find and fix bugs with the AI, and undo mistakes with Git
- Secure the basics: sign-in, row-level access rules and secret keys kept out of code and the browser
- Deploy the app, watch errors and costs, and know when to hand over to an engineer
Syllabus
6 stops, about 3.5 h in total. Each stop fills in when you complete the lesson.
What AI coding tools can and cannot do
AI coding tools can turn a plain description into a working screen in minutes. They can also hand you a beautiful app that saves nothing and shows every customer's data to everyone. This lesson explains how the tools work, the three kinds you can choose from, what they are good and bad at, and how to pick one for the reorder app you will build in this course.
AI coding assistantsNo-code and low-codePrompting for code
A spec the AI can follow
An AI coding tool builds what you describe, and it fills everything you leave out with a guess. This lesson shows you how to write a one-page spec for Ravi's reorder app (users, screens, data, rules and checks), keep it in the project where the tool reads it, and make the AI ask questions and plan before it writes a line of code.
SpecsPrompting for codeAI coding assistants
Building in small steps
An AI coding tool can write a whole app from one long prompt, and the result usually looks finished long before it works. This lesson gives you the loop that keeps you in control: plan, build one step, check it, save it, and only then move on. You will use it to build Ravi's reorder app one feature at a time.
AI coding assistantsPrompting for codeSpecsGit save points
Reading and fixing what the AI wrote
The AI builds a screen in two minutes, and it works when you click through it. Then a real shop owner uses it, and the total is one cent short, or an order arrives twice. This lesson teaches you to read code well enough to find where things go wrong, to debug with the AI in a calm routine, and to use Git so that no mistake is ever permanent.
DebuggingReading codePrompting for codeGit basicsAI coding assistants
Data and security basics
An AI tool can build a working reorder app in an afternoon, and that same app can show every shop's orders to anyone who knows where to look. This lesson shows you where your app's data lives, how sign-in and database access rules keep each shop inside its own rows, and how to keep secret keys out of your code, so Ravi's orders stay Ravi's.
App security basicsDatabase access rulesData modeling basicsSecrets and environment variables
Ship it and know your limits
An app on your laptop helps nobody. This lesson puts Ravi's reorder app on the internet for five partner shops, shows you how to watch it, what it costs, how to undo a bad change in minutes, and how to tell when a prototype has done its job and an engineer should take over.
DeploymentApp security basicsDebuggingAI coding assistants
Capstone: Vibe-code a reorder app for partner shops
A realistic project with a rubric and a model answer.
Final exam and certificate
10 questions drawn at random, 70% to pass.
Capstone project
Vibe-code a reorder app for partner shops
Ravi runs a partner corner shop and reorders the same items from Mangrove every week by phone, and about one phone order in twelve has to be corrected after delivery. Build him an app, mostly with AI tools, that remembers his usual order, lets him change it and send it in three taps, and shows his order history. Use sample products and at least two test shops. Write the spec first, build in small committed steps, set up sign-in and row-level access rules so a shop sees only its own orders, keep every secret key out of the code and the browser, deploy it, and keep a review log of what the AI got wrong.
You will hand in
- A one-page spec with users, screens, data, rules, acceptance checks and what is out of scope
- A deployed app with sign-in, and the repository with its commit history
- A review log: at least three things the AI got wrong, how you found each one and how you fixed it
- A short security check: what each test shop can read, where the keys live, and how you tested it
Check what you know
Already know some of this? Answer 6 quick questions, one from each lesson, and we will mark the lessons you can skim. It takes about 3 minutes and nothing is graded.
Questions
Do I need to know how to code?
No. The AI writes most of the code. You will learn to read it well enough to check it, ask the right questions and spot the mistakes AI tools make most often, and the small browser exercises are explained line by line.
Which AI tool do I need?
Any current AI coding tool works: a browser app builder, an AI code editor or a coding agent. The first lesson explains the three kinds and when each fits. Several have free tiers, but their limits change often, so check before you start.
Is vibe-coded software safe to use?
Only if you check it. A whole lesson covers sign-in, row-level access rules and secret keys, the places AI-built apps most often go wrong, and the last lesson covers when to bring in an engineer.
I'm already a developer. Is this for me?
Yes, if you want a careful way to work with AI tools: specs the tool can follow, small committed steps and reviews. Working with AI Coding Assistants in AI Systems for Builders goes deeper on instruction files, reviewing AI pull requests and CI.
Is there an exam and a certificate?
Yes, and both are free. Each attempt mixes scenario questions with practical tasks such as ordering the steps of a feature build or fixing a small bug the AI wrote. You pass with 70% on the questions and an average of 70% on the tasks.
Is it really free?
Yes. Every lesson, podcast episode, exercise, quiz, final exam and certificate is free. The labs and their templates for real work are free too. Plus and Premium add every lab challenge, weekly extras and a mentor on top, and they never lock the tools or the courses.
How long does it take?
Each lesson shows an honest time for reading and doing. Most people finish a course in two to four weeks at three or four hours a week.