---
title: 'Twenty Twenty Sprints'
description: 'How I structure my day in 2x20-minute sprints an hour -- a pomodoro shape that fell out of AI coding.'
---

My day now runs on a simple cadence: two 20-minute sprints an hour, with a 10-minute gap. It fell out of my AI coding workflow and ended up looking a lot like a pomodoro.

In each block I kick off a set of tasks, nudge them forward, and then "burn down" any threads that can be closed out. If I have any long-running tasks (refactors, upgrades, experiments), I'll set them off to come back to in the next block.

Twenty minutes is long enough to get into something, but short enough to achieve a real outcome. The shape aligns with my intention of optimizing for [Single-Prompt Outcomes](/no-agents-no-plan/) — I shape each prompt to land as close to "first time" as possible[^3].

To make this work I keep a large number of features in flight in parallel. With ~20 open tasks across branches and worktrees[^2], there are always a bunch of plates spinning. By the time I finish a sprint on one thread, another has produced something worth looking at.

<picture>
  <source srcset="/images/2026-05-12-twenty-twenty-illustration-dark.png" media="(prefers-color-scheme: dark)">
  <img src="/images/2026-05-12-twenty-twenty-illustration-light.png" alt="Sprint, rest, sprint, rest" style="width: 80%; height: auto; display: block; margin: 0 auto;">
</picture>

**In the break I step away from the computer**. This is time for a walk, cleaning the kitchen, coffee, exercise, calling a friend[^1]. Even if I "work", I'll do it in my notebook on paper.

I do miss the "deep work", but this approach produces a more balanced day. I'm not "beast mode" programming. I'm not smashing things out, headphones on, for hours in a stretch. Instead, I'm kicking off a thread and then casually thinking it over while I clean the kitchen. Usually I come back to completed work, or with a clearer head on what needs to happen next.

Here are some keys I've found to make this work:

- **Plan your day**: I use pen and paper. I start the day by mapping out the features I want to work on, and the coarse chunks that make sense. It's lo-fi, but effective.

- **Plan your downtime**: Otherwise you'll end up browsing the Internet or scrolling socials. Write down the people you want to call, the chores around the house. Have a set of tasks to do and feel good ticking them off (one or two blocks on socials is fine!). Stepping away from the computer in spells will _improve_ your output, I guarantee.

- **Straight to Codex**: As soon as you think of a "chore", drop it [straight into Codex or Claude](/straight-to-claude/). Half the time I do this on my iPhone or iPad while I'm out. Once I get to my desk there is already a set of work to burn down.

### FOOTNOTES

[^1]: Yes, sometimes this exceeds 10 minutes, that's fine. I usually am able to get back on pace with minor adjustments along the way.

[^2]: From my [current AI workflow](/my-current-ai-workflow/) -- ~20 open tasks is my sweet spot for balancing parallelism and WIP.

[^3]: I rarely use PRDs. I'm doing design, product, and engineering in one, so that's a luxury in some senses. I use [Battleship Prompts](/battleship-prompts/) to give a good chance I'll get an outcome from most prompts. If something doesn't land, I throw it away.
