zlacker

I think use cases like that will be where "AI" has the biggest wins.

That's a task that I could automate as a developer, but other than LLM "vibe coding", I don't know that there's a good way for a lay person to automate it.

>>jlaroc+(OP)
There are two forms of business software gen AI coding is 100% going to eat:

   1. Simple CRUD apps
   2. Long-tail / low-TAM apps

Because neither of these make economic sense for commercial companies to develop targeted products for.

Consequently, you got "bundled" generalized apps that sort of did what you wanted (GP's example) or fly-by-night one-off solutions that haven't been updated in decades.

The more interesting questions are (a) who is going to develop these new solutions and (b) who is going to maintain these new solutions? In-house dev/SRE or newly more-efficient (even cheaper) outsourced? I'd bet on in-housing, as requirements discovery / business problem debugging is going to quickly dominate delivery/update time. It already did and that was before we boosted simple app productivity.

>>ethbr1+jX
> I'd bet on in-housing

I wouldn't.

Knowing what to build is part that many businesses struggle with.

As much as consultants are lambasted, my experience of companies is that they struggle to develop or maintain anything in-house - even where it should theoretically make economic sense. >>46864857

>>roboca+au3
There would definitely need to be new positions / roles hired internally.

I imagine "vibe coder" will eventually coalesce with business requirements analyst, into a sort of "LOB developer-lite." I.e. every low-code products' undelivered citizen developer dream.

You need someone in the technical details and with some developer background (thinking through edge cases is a hard skill requirement), and you need someone with the process analysis and documentation skills (as well as the ability to push back / simplify requirements where it makes sense).

External developers/consultants are typically terrible at the requirements discovery and specification stage, because they're not embedded day-to-day with the business. Ergo, you get stupid feature decisions because someone left a sentence off a doc.

From your other comment, I think you're thinking about more complex / core / feature-rich solutions than I am. I agree those may remain SaaS / outsourced.

But there's no way in hell dirt-simple CRUD and "I am the only person in the world who has this need" solutions stay out of house.