GitHub

AI coding? Vibe coding? Agentic coding?

All those terms are pretty similar. But basically AI coding is about using AI models (specially LLMs these days) and all the tooling around it to help you write software. It's also called "AI for code generation" or "code gen" for short, and there's an entire fascinating field of research and engineering, that dates back to 1950's when we used Lisp to generate code.

How can I use it?

You can use AI coding in many different ways, but in summary: AI is your copilot: you use AI models to augment yourself, to boost your productivity.

How I prompt for coding? AKA How I vibe code?

Before mid or end-2025, it was really common to LLMs hallucinate and enter in endless cycles to fix errors. Nowadays the models are really good, but it's still interesting to follow basic principles when using them to code: Do not ask everything in one prompt.

What to do when the dreaded "rate limit" message hits?

Switch to a different model. There are at least two different reasons this can happen. You can make a heavy request that exceeds the model's input/output token limit. Or, if the server cluster it's running on is having a bad day, you may be throttled to reduce the load. The error messages you get are often not transparent about this. You can find a more detailed explanation here.

How do I set up project-wide rules?

You can define rules or conventions that will be applied to your project by "injecting" them in the context of the LLM. Each editor have some ways to do it: For almost any agent except Claude Code, create an AGENTS.md file in the root folder of your project.