I used one for outbound and it was pretty good (it even sold a 50$ report it created). Currently using one for research.

I like that the agents are "learning". While the first emails were pretty trashy, I let him research on how to improve them to not sound too generic etc. The results were quite impressive.

You should follow @simonw Here's his procedure https://til.simonwillison.net/llms/openclaw-docker

I'm not really using it yet because I can do it by myself. So far I have time over money

I felt the same way. I was rolling my eyes at the hype, but reading about things like OpenClaw or Cursor is totally different from experiencing them. If you have any old repos out there — try running an agent on them, you might actually be amazed.

I'm not sure I buy the long-term "90% productivity" claims for complex, legacy enterprise systems, but for the boilerplate, libraries, build-tools, and refactoring? The gain is gigantic. All the time-consuming, nerve-wracking stuff is mostly taken care of.

You start off checking every diff like a hawk, expecting it to break things, but honestly, soon you see it's not necessary most of the time. You just keep your IDE open and feed the "analyze code" output back into it. In Java, telling it to "add checkstyle, run mvn verify and repair" works well enough that you can actually go grab a coffee instead of fighting linter warnings.

The real question it raises: If your competitor Y just fired 90% of their developers to save a buck, would you blindly follow suit? Or would you keep your team, use this massive leverage, and just dwarf Y with a vastly better product?