Vibe Coding

Building software primarily through natural language.

Vibe Coding is taught here in 13 lessons, running from The vibe coding practice through to Shipping, documenting and maintaining an agent-built project. Each lesson takes one topic, shows the working code, and links onward to the next, so the course can be read straight through in order.

Lessons

1. The vibe coding practiceBuilding software by describing intent in natural language and reacting to what comes back, rather than typing every line.
2. When it works and when it failsThe conditions that make agent-written code succeed, and the failure modes that make it expensive.
3. Keeping quality with tests and reviewPractices that keep agent-assisted changes shippable: tests as the contract, review as the gate, types as the first filter.
4. Prompting for intent, not syntaxDescribe the outcome, the constraints and the definition of done, and iterate on the prompt instead of discarding it and starting again.
5. The generate, run, correct loopSmall increments, real execution, real error output pasted back, and verification in the running application rather than in a summary.
6. Choosing a stack that agents handle wellConventional frameworks, typed languages and well-documented libraries cost far fewer attempts, and that difference compounds across a project.
7. Version control as your safety netCommit before you generate, keep one intent per commit, branch per experiment, and read the diff before you accept it.
8. Specs and tests as the contractWrite the requirement first, turn it into a failing test, and let the agent drive it to green - including the edge cases it would otherwise skip.
9. Types, linters and static checks as the first filterAutomate the mistakes an agent makes most often, and wire the checks into the loop so the agent fixes them before you ever read the diff.
10. Reviewing generated code like an ownerSpot the plausible-but-wrong patterns, check the error paths and boundaries, and know when deleting the work is faster than correcting it.
11. Debugging when the agent goes in circlesRecognise a poisoned session, restart cleanly, supply evidence instead of opinions, and reduce the problem until it is obvious.
12. Security, secrets and dependenciesThe specific security mistakes agents make, why credentials must never enter a prompt, and how to review an added package.
13. Shipping, documenting and maintaining an agent-built projectWrite documentation a person can follow, be honest about authorship in review, and pay down generated debt before a rewrite is the cheaper option.

More in AI & Intelligent Development

AI Basics AI Agents Math for AI Machine Learning scikit-learn TensorFlow PyTorch Natural Language Processing LangChain Ollama OpenCV Codex Claude Code OpenCode Selenium Playwright

FAQ