How to start coding with AI agents

You probably hear about AI agents everywhere these days. The news about AI are overwhelming, yet many engineers haven't switched to agentic coding yet, or even tried it out. Below is a full guide to get you started coding with AI agents and understand why it's really a big deal.

Agentic coding means talking with AI through a chat UI and seeing it implementing and running code for you. Just like if you hired a developer who works for you and livestreams all the results. Agents have access to your system and can run bash commands for you, such as `npm install`, `chrome http://localhost:5173`, `git push`, or `rm -rf /`.

Previously, AI was mostly used as a tab-completion tool for coding. But in the last months of 2025, LLM models became much better and more powerful, and now can produce great code and are super useful to iterate faster and build quality products.

Now you can actually build a production-level system if you approach “vibe-coding” as an engineering task, but not as some out-of-control slop beast. World-class engineers code with AI: Linus Torvalds (Linux Creator), DHH (Ruby on Rails creator / Basecamp founder), Gergely Orosz (running the large engineering newsletter) and so many others.

Huge companies like Stripe already merge thousands of AI-generated PRs per week. It's now a matter of time until it comes to you, so you better start early.

AI won’t magically write a perfect project for you right away (yet). You need to configure it.

Agents are capable of working on complex tasks and projects, following comprehensive coding guidelines to produce lots of quality code faster.

But the style and output quality depend on you, as you need to configure your agent’s context to create exactly what you need. This is hard to do if you don’t follow a system in your code, but luckily you can use open-source configurations from others, e.g. React Best Practices from Vercel.

If you don’t have any rules or prompt system, chances are you’ll end up with slop. But now it’s on you, not AI.

Context Engineering is the process of loading information into your AI agents. The thing is: LLMs are limited in the context size that they can process, and their output becomes much worse if you use it unwisely. Also, it costs money.

The art of engineering today is the art of creating the best context architectures and writing thoughtful rules. Learn to write less code, but start writing more context-enhancing documents on how to write code.

Use Skills, Rules, and Commands to automate common actions and enforce coding guidelines. Write down rules in Markdown as soon as you repeat something twice to an agent. This is a new DRY.

Subagents let you automate multiple roles, e.g. front-end, back-end or tech writer. You can create different context directories per agent to fine tune common operations. You can tag a specific agent to activate it and run them in the background or foreground depending on the task. This way you’re kinda working with a team of developers who follow your instructions.

To use AI agents, you need to install them into your system, so it can work with your files and call terminal commands.

With general purpose agents, you can use different LLM models. Some models work better than others on specific tasks; you should find out which ones work best for you. For example, Gemini works great for front-end code. Codex great for large codebases. Claude Opus is great for backend code and now in general is considered the state of the art.

Note: you can use your Copilot and Codex subscriptions with OpenCode (but not Claude Code sub or Antigravity).

All AI agents are paid. Basic plans start from $20/mo. Copilot starts at $10/mo.

If you produce lots of code (e.g. building a startup), you’ll likely hit limits soon and will need to upgrade to common $100/mo or $200/mo plans.

Learn to craft the best contexts and optimise for tokens.

Engineering has most definitely changed. Now it is the best time to learn the new ways of building, as it's still early. You'll need to unlearn your previous workflows, and it will be painful. But it is well worth it for your productivity and future career.

The only way to learn how to code with AI is to actually build something with AI.

If you can't use AI on your work project, then build a side project. Go crazy and try all the features to understand which ones are most useful. Test different models. Run 10 agents in parallel. Write skills and craft context to see how it changes the output.

Connect with other engineers building with AI and create something cool together.

Just like with any skill: you need to learn and practice, and it takes time!

PS Learn to write well. Markdown is the new JavaScript.