Two months ago I asked here how people stay aware of what their agents are doing, and @getosmo replied with something that has been quietly rearranging my roadmap since.
I had been treating "can you undo it" as the line for when an agent should stop and ask. He took that apart. Irreversibility over-fires and under-fires, he said. It over-fires on things that cannot be undone but that nobody cares about, like the agent writing a log line. It under-fires on the ones that really hurt: a mass email to 50k users, or a migration you can only roll back after downtime. "Reversible on paper, ruinous in practice."
It doesn't even have to be a big dramatic failures, more the small moments where something clicked and you went from trusting the output by default to double checking everything. For me it was watching an agent confidently rename a function across twelve files, then leave the original function untouched in a thirteenth file it apparently didn't search, with zero indication anything had been missed. It wasn't even a hard case, the file just wasn't in the directory it happened to grep first. What was your moment? And did it actually change your workflow afterward, or did the trust creep back in after a week like it always seems to for me?
When you're a first-time founder/maker, and you're the only person using your own product, you probably overlook important things. That's why you need to test the product with as many people as possible.
The problem is that time is limited. You have to decide not only how many people will test it, but also who those people should be.
