---
title: 'Software that gets built and tested while I sleep'
canonical: 'https://www.dealmobile.co.uk/writing/software-that-builds-while-i-sleep'
url: 'https://www.dealmobile.co.uk/writing/software-that-builds-while-i-sleep'
type: Post
published: '2026-11-04'
summary: 'I leave software to build and test overnight, and nothing lands unless the tests and a review agree. Routine steps go to cheap and free models, including a large one on my own laptop, and Claude does the design and the review. Measured figures from 24 October and 3 to 4 November 2026.'
---

# Software that gets built and tested while I sleep

Published 2026-11-04

![Built and tested while I sleep. Three features built overnight on 24 October 2026, each merged after review. The local model’s first job passed first time for $0. Outside models cost about $0.34 in one long session. Nothing merged without me.](https://www.dealmobile.co.uk/sites/default/files/styles/almanac_shot_md/public/content/images/posts/software-that-builds-while-i-sleep/hero.png.webp?itok=CfjsMD61)

In the evening I plan a piece of work, approve the plan and leave it running. In the morning I read what came back. Nothing has been merged without me.

The job runner is my own. It’s called [Mullet](https://www.dealmobile.co.uk/projects/mullet.md), and I’m not going to describe how it works. Here is what it does.

On the night of Saturday 24 October 2026, during a weekend of focused work on my personal projects, it built three of its own features. Each was a plan of five to seven steps, and I merged each one only after reading the diff.

## Who does what

Claude does the design and the review. The routine steps go to cheap and free models, and one of those is a large coding model that runs on my own laptop’s graphics card.

On 3 and 4 November 2026 that local model did its first real job for me: two small fixes across three files. It passed every check on the first attempt in about three and a half minutes, and it cost nothing. That is one job, a sample of one.

In the same long session, the outside models I used for delegated work cost about $0.34 in total. That figure is from Mullet’s own record, and I haven’t checked it against the providers’ bills.

## Why it’s safe to use cheap models

The saving isn’t the point by itself. A cheaper model is only worth using if something independent checks what it did, and every change here faces the same checks whoever wrote it. A wrong attempt costs time and tokens, and it doesn’t reach my code.

That is the rule I hold the whole setup to, and it has its own post: [the rule that lets me trust work I’m not watching](https://www.dealmobile.co.uk/writing/the-rule-that-lets-me-trust-unattended-work.md).

- **Projects:** [Mullet](https://www.dealmobile.co.uk/projects/mullet.md)
- **Tags:** [AI](https://www.dealmobile.co.uk/writing/tag/ai.md), [Testing](https://www.dealmobile.co.uk/writing/tag/testing.md), [Mullet](https://www.dealmobile.co.uk/writing/tag/mullet.md)

---

Index of this site: [llms.txt](https://www.dealmobile.co.uk/llms.txt)