cd /news/ai-agents/5-things-i-learned-letting-an-ai-cow… · home › topics › ai-agents › article
[ARTICLE · art-144225] src=dev.to ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

5 things I learned letting an AI coworker run my Windows PC in the background

A Seoul-based solo founder with no programming background built a local AI coworker that runs in the background on his own Windows PC, reading application controls directly rather than relying on screenshots so it can work while he keeps using the machine. In his own logs, trimming oversized tool results fed back to the model cut payload size from 668,083 to 95,131 characters (about 86% less), and over three days 227 jobs were dispatched to parallel AI workers with 84% of 378 requests completed end to end. He says the project has no paying customers yet and he is seeking small pre-seed backing.

by read2 min views1 publishedOct 3, 2026

I'm not a programmer. I ran cafes and a convenience store before this. For the last few weeks I've been letting an AI coworker I built (by intuition, with a lot of help from AI) do real work on my own Windows PC every day: filling web forms, organizing files, managing a small game project and video jobs.

Here is what surprised me, with numbers from my own logs only.

Most "computer use" demos take a screenshot, think, click, take another screenshot. That is slow and it takes over your screen. Mine reads the app's controls directly instead of looking at pictures, so it works in the background while I keep using the PC. Finding and playing a YouTube video takes about 1-2 seconds.

When I measured, the biggest cost wasn't the model's answers. It was huge tool results (page dumps, logs, long file reads) being fed back to the model. Across 24 real tool calls, what it sent went from 668,083 to 95,131 characters: about 86% less. That changed speed and cost more than switching models did.

I stopped wanting a "yes?" before every click. What I kept: a check before paying, deleting or messaging someone, and one hard rule: when I say stop, it stops, and it never silently repeats something it isn't sure finished.

Over 3 days it handed 227 jobs to parallel AI workers. When I ran a game project as 8 parallel teams, each team finished 88-100% of its tasks. One assistant doing everything in a row was the bottleneck.

It keeps long-term memory in Korean and English with the original records, and after a restart it resumes the interrupted job instead of starting over (it had to do that several times today alone). Over 3 days I sent 378 requests; 84% were finished end to end. The other 16% taught me more than the successes.

Honest status: solo founder in Seoul, no paying customers yet, looking for small pre-seed backing. Short overview: https://telegra.ph/ARCHE---local-AI-coworker-10-02

If you just need a small job done the same way, I take a $25 one-day Excel / file automation script: https://ko-fi.com/manmuli/commissions . Or buy me a coffee at https://ko-fi.com/manmuli if this was useful. Written with AI assistance: my English isn't good, so my AI coworker drafted this from my notes and logs.

── more in #ai-agents 4 stories · sorted by recency
── more on @arche 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/5-things-i-learned-l…] indexed:0 read:2min 2026-10-03 · —