Skip to content

Note

May 14, 2026

2 min read

Confession from the AI-assisted builder trenches

By Cristiano Pierry

A reflection on AI-assisted building, taste, product judgment, and the gap between a working prototype and a useful product.

aiproduct-managementworkflowcodex

I recently asked Codex to help me build something.

The functionality was there. The bones were there. The UI, however, looked like it had been assembled during a fire drill by a spreadsheet with separation anxiety.

So I typed:

“I don’t know which design school you went to but I don’t want to hire anybody from the design school ever again.”

Not proud of that.

No actual design school was involved. No designers should be blamed. Codex does not have feelings, tuition debt, or a portfolio site. Still, that was not my finest prompt.

And it reminded me of something important about building with AI.

AI can compress the path from idea to prototype. It can help you write code, generate variants, connect workflows, summarize research, and get to a working version faster than ever.

But it does not remove the need for taste.

It does not remove the need for product judgment.

It does not remove the need to ask: is this actually useful, understandable, elegant, trustworthy, and worth putting in front of a human being?

In fact, AI may make those things more important.

Because now we can generate bad ideas faster. We can ship confusing experiences faster. We can create technically correct but emotionally strange products faster. The machine can help us move quickly, but it cannot always tell us whether we are moving in the right direction.

That is still the builder’s job.

Especially in discovery, personalization, search, and AI-enhanced experiences, the gap between “it works” and “it helps” is everything.

A recommendation that technically ranks content is not the same as one that understands intent.

A search result that matches keywords is not the same as one that helps someone decide.

A chatbot that responds quickly is not the same as one that makes the experience better.

And a prototype that compiles is definitely not the same as a product with taste.

I’m not always the version of myself I want to be when a tool hands me beige buttons, mystery spacing, and a modal that looks like it escaped from 2011.

I’ll do better next time.

Probably.

But the bigger lesson stands: AI is changing how fast we can build. It is not changing the need to care about what we are building.

A demo gets applause.

A useful workflow gets adopted.

A product with taste gets remembered.


This writing reflects my personal perspectives on product management, AI, and content discovery. It does not represent the official position of my employer or any affiliated organization.