Does "move fast and break things" ruin AI agents?

Inument
New Contributor II

Is the "move fast and break things" startup mindset actually fatal for custom AI agent development?

I read that rushing MVPs creates massive tech debt and unstable guardrails that cause projects to crash by year two.

Have any of you hit this "year 2 wall" with your AI projects or had to completely rethink rapid deployment?

Inument

Rjdudley
Honored Contributor

Well, you can only break things which exist, so if you're delivering an MVP, nothing yet exists to be broken.  This is kind of the wrong mindset, I think you should look at the agile process of "ship fast, ship small, iterate".  Sometimes the iterations are you implementing a guardrail or tuning a system prompt but you're making a lot of small changes quickly and getting lots of feedback from your users.

View solution in original post