Vent: My AI customer service bot in Portland kept gaslighting my own clients

I run a small plumbing company and last month I set up an AI chatbot to handle after-hours calls, thinking it would save me from angry voicemails. Turns out it was confidently telling people their leak could wait until Monday, even when they said water was pooling in their basement. One customer quoted it back to me, saying 'your system said it's low priority,' and that's when I realized I had to test the bot with worst-case scenarios before trusting it. I've since added a keyword override for 'emergency' and 'leak' that routes straight to my cell, but I'm wondering if anyone else has had to put training wheels like that on their AI tools, or if I'm just overthinking it?

1 comments

1 Comment

emma76820d ago

Wait, is the AI really the problem here, or is it the way we expect it to handle something it was never built for? I get that you're frustrated, but a chatbot that's just reading scripted answers isn't going to know when a basement flood is a bigger deal than a dripping pipe. That's called judgment, and no bot has that yet. You basically asked it to do a job that needs human brain power, and then got mad when it failed at that. The keyword override is smart, but honestly, why not just have a real person on call for after-hours emergencies? It's a few extra bucks a month, but it saves you from this exact mess. You're not overthinking it, but you might be under-thinking what you're handing off to a machine.