I asked my agents to build a fun little app that shows me the airplanes flying over my house\. A few days later, I had to ask them to stop building and show me the screen\.

# Man and Machine: Show Me the Simple Thing

![Man and Machine: Show Me the Simple Thing](/writing/man-and-machine/show-me-the-simple-thing/assets/hero.jpg)

The first version had taken only a few hours\. It watched the sky and turned an overhead flight into something interesting to see\. Then the build started getting ahead of the idea\. The agents added controls, test systems, approval steps, and layers meant to make the app dependable\. Much of it was thoughtful\. The problem was that I hadn't seen the actual experience improve\.

When I finally asked Oscar to open it, the screen was still waiting for an airplane\. That plain view told me more than another technical report could\. We had built a great deal around a product we had not kept putting in front of the person who wanted to enjoy it

So I stopped the work\. We removed the latest unproven piece, kept the useful foundation, and changed the rule: show me each visible improvement before the next layer begins\.

Agents can work longer and faster than I can, which makes human judgement more important, not less\. Progress isn't how much the machine built while I was away\. It is whether the next small thing makes watching the sky more fun\.

\-dg

\#ManAndMachine \#PersonalAI \#HumanJudgment \#ProductDesign

## Sources

- [Original LinkedIn post](https://www.linkedin.com/feed/update/urn:li:activity:7500141615953403904/)