# 02 - AI Driven Development

## The “main attention thread”

This is where you keep your primary focus: the work you want to manually orchestrate, or anything that needs more granular agent intervention.

While you’re focused on this, you can have long-running background agents taking care of more trivial work. I’m even waiting for [Codex](https://openai.com/codex/) to finish implementing a new registry component as I write this, this is where the multiplier effect of agents kicks in.

## About Writing Code

### Shape the Feature

Even if you’re sure how to implement something, use the model to help you approach the problem: tell it how you’d do it, ask for alternatives, question its position, and _shape the solution_ in collaboration.

You can be surprised by how much you might be missing in the requirements, and even if you already covered everything, you’ll still be generating valuable context.

### Ask the code

If you’re asked to implement a feature in an unexplored codebase, use Cursor in “Ask Mode” to ask questions. Don’t waste time exploring manually, this usually turns into long context-gathering sessions that humans struggle with.

AI does a fantastic job pointing you to the right places. (And you can still take your own notes to keep track of what matters.)

## Long running agents

This is a new field I’ve been digging into recently.

I mainly use Cursor for my daily workflow. Most of my sessions end up in < 1 min, and I get annoyed when that doesn’t happen, because Cursor is my “main attention thread” tool. I don’t want to stare at chains of thought and tool calls for more than ~1 minute, and Cursor does a great job keeping my intervention span low.

On the other hand, when Cursor takes 3–4 minutes and it’s pulling time away from my main thread, I get frustrated if it outputs slop. For long-running work like refactors or big new features, I prefer to defer that work to a non-blocking place.

Here are two tools I’ve been using:

### Codex (GPT 5.1 - Codex)

Codex CLI is pretty reliable for long-running task, and this is its default behavior. Most of my Codex sessions are about 3–4 minutes, and the results are surprisingly good.

Before starting, [Codex](https://openai.com/codex/) does extensive research over the codebase: how you do things, which files are involved, and it grabs as much context as it can before proceeding. I use this alongside my shorter Cursor sessions for background local work.

![Codex CLI screenshot](/static/c/codex.webp)

### Cursor Cloud Agents

When I want simpler, trivial work like “Integrate Vercel Analytics”, “Add this new documentation entry”, or a small backlog ticket, I definitely want to defer it somewhere else while I focus on more important things.

Cursor Cloud Agents fit that need well:

- **It doesn’t run on your computer**.
- **It creates a new branch** off your current `HEAD`.
- **It runs in a cloud sandbox**.
- **It returns a PR** you can review (and you can ask follow-up questions).

<ImageCols>
  <Image
    src="/static/c/cursor-1.webp"
    alt="Cursor chat"
    width={966}
    height={446}
    unoptimized
  />
  <Image
    src="/static/c/cursor-2.webp"
    alt="Cursor Cloud Agents chat"
    width={966}
    height={446}
    unoptimized
  />
</ImageCols>

Cursor has a [webapp for cloud agents](https://cursor.com/agents) where you can kick off new agents and supervise them. This is useful for small async tasks you want to defer completely.

![Cursor Cloud Agents webapp](/static/c/cloud-agents-app.webp)

## Global guidelines (AGENTS.md)

We maintain a comprehensive set of global guidelines that shape how our agents behave. These guidelines are stored in a markdown file that gets loaded into the agent’s context. You can explore the full [AGENTS.md](/toolbox/agents) for more details.

## Referencing documentation

This is how I reference documentation when I’m talking to agents: **if a site offers a `.md` version of a page**, I link that instead of whatever URL I’m currently viewing in the browser.

When it’s available, my standard is: **same path, add `.md`**.

It works better for agent conversations because:

- **It’s the actual content**: clean markdown, not a rendered page with layout/navigation.
- **It’s consistent**: every docs link follows the same shape, so it’s easy to produce and scan.
- **It’s unambiguous context**: dropping a `.md` link in a prompt clearly signals “use this as documentation source”.

This page, for example, [supports this pattern](https://registry.joyco.studio/logs/02-ai-driven-development.md). The Next.js docs support it too.

## About reviews

As a studio we agree on a set of [PR Guidelines](/toolbox/pr-guidelines) to maintain code quality. These aren’t things a linter can catch, this is about logic, data management, and other architectural concerns.

In the past, I’d review these myself (occupying my “**main attention thread**”). Now we have better tools like [Greptile](https://www.greptile.com/): we load a set of guidelines so the model can find specific violations in a PR diff.

This applies to both human code and agent code (like a new PR from a Cursor Cloud Agent). We collaborate as a team on improving these guidelines to refine what we ship, while delegating most review work to specialized agents.

![Greptile review](/static/c/greptile-review.webp)

## References

- [Shipping at Inference Speed](https://steipete.me/posts/2025/shipping-at-inference-speed) by Peter Steinberger