I m restyling a live app screen by screen, with Claude Code doing the edits. My test suite has 262 tests and all of them pass, but none of them check how a page looks. So a change to shared styles could break a screen and nothing would tell me.

Before each change, I have the agent screenshot every screen I m not supposed to touch, using a fake signed-in session and mocked API responses so no real data is involved. After the change, it captures them again and compares them pixel by pixel. Anything that differs has to be explained.

That caught something I would never have seen. 34 screens matched exactly. One modal didn t: 1,334 of about 215,000 pixels were different. To my eye, before and after looked identical. The cause was that my first version moved the page into a new wrapper, and the old container had been quietly centering the modal s heading. The new one didn t. No test would have complained.

It also showed that a modal kept outside the new wrapper still changed colour, because my theme variables are set on the whole page, not just the wrapper. I had to re-scope the old colours around the modal.

One of the most common questions I get from founders is:

Which day should we launch?

I've used ChatGPT and other AI tools while building my startup, and they've made it possible to take on work that would normally require a much larger team. Research, technical problem-solving, planning, and exploring new ideas can happen much faster. But one thing I've learned is that completing more work doesn't necessarily mean the business is moving forward at the same speed. You can build faster, solve technical problems faster, and make improvements faster, while the harder questions about customers, adoption, and business growth still take time to answer. It's changed how I think about productivity as a founder. I'm learning to distinguish between how much work gets completed and whether that work is actually moving the business forward.

For founders building with AI, what's one lesson you've learned about the difference between moving faster and making real business progress?

In our first six months, whenever a paid user churned, our immediate reaction was: Ah, they needed Feature X. Let s build it."

Our backlog became a graveyard of quick fixes requested by churned users. Yet, retention stayed flat.

It took us a painful realization to see that the issue wasn t a feature gap; it was a friction gap. The product required too many context switches from our users' daily routines.

For founders who survived this phase: How did you shift your team's mindset from "ship more features" to "reduce workflow friction"? What metrics actually helped you spot this early?

I remember there was a time when the Product Hunt team had a subcategory called AMA, which felt a bit more exclusive.

A special guest would show up with a post like I m X, founder of X, AMA, and those sessions were actually quite successful in my eyes.

The growth example hits home because AI is terrifyingly good at agreeing with whatever hypothesis you feed it.

If your starting prompt is biased, the tool will just find data to make you feel smart about a wrong decision.

True collaboration only happens when you force the model to look for counter-arguments or blind spots you missed. Have you found a reliable way to get AI to challenge your strategy instead of just echoing your thoughts back to you?