Build Software. Build Users (dima.day)

This is interesting, and I think worth trying. However,

    The process is iterative:

    Vibe code users <--> Vibe code software

    Step by step, you get closer to truly understanding your users

Do not fool yourself. This is not "truly" "understanding" your "users". This is a model which may be very useful, but should not be mistaken for your users themselves.

Nothing beats feedback from humans, and there's no way around the painstaking effort of customer development to understand how to satisfy their needs using software.

This is ridiculous. I doubt this would work with a general AI, but it surely cannot work with LLMs who understand exactly nothing about human behaviour.

Another fart in the wind. How to write lots of “programming philosophy” and say nothing.

Good point. I think it is the time to remove the line between the engineering and product management completely. Because, we can.

A bit too vague to be useful advice don't you think?

Why not show some actual examples of these agents actually doing what you describe. How exactly would you set up an agent to simulate a user?

Yeah, I have build a Product hunt alternative for solo founders - Solo Launches to give them visibility. I built 290+ users from it till now and its free and giving a good DR dofollow backlink. https://sololaunches.com

I like the idea. As a solo dev I've experimented with creating Claude subagents for multiple perspectives for "team leads" and will run ideas through them (in parallel). The subagents are just simple markdown explaining the various perspectives that are usually in contention when designing stuff. And a 'decider' that gives me an executive summary.

  agents/
    |-- customer-expert.md - validates problem assumptions, customer reality
    |-- design-lead.md - shapes solution concepts, ensures UX quality
    |-- growth-expert.md - competitive landscape, positioning, distribution
    |-- technical-expert.md - assesses feasibility, identifies technical risks
    |-- decider-advisor.md - synthesizes perspectives, executive analysis

> LLMs likely have a much better understanding of what our users need and want.

They don't.

Basically this sounds like Agentic Fuzz Testing. Could it be useful? Sure. Does it have anything to do with what real users need or want? Nope.

Pretty radical idea, love it! Definitely going to give this a try