A beta tester told me my AI chatbot sounded like a bad infomercial, so I rewrote the entire greeting system

I spent 3 months on this assistant. Thought the tone was fine until someone sat down and read 10 responses out loud. Every single one started with "Great question!" or "Happy to help with that!" All fake polite corporate nonsense. I stripped out all the forced enthusiasm and just made it say what it needs to say. Users still complain it's "cold" but at least nobody thinks they're on a sales call. Has anyone else had to dial back the cheerfulness to get better results?

3 comments

3 Comments

emerychen13d ago

Three months sounds about right, I've had similar issues with my own little project. Thing is, "Great question!" isn't really fake polite corporate nonsense, it's more like a reflex people picked up from too many YouTube tutorials. Making it strictly functional might actually be too far the other way though, you need some kind of middle ground.

christopher_flores4613d ago

Noticed the same reflex in customer service too, always gotta find that middle ground.

caseys3013d ago

Caught a podcast where some dev was saying "Great question!" is basically a holdover from old forum culture where you had to be overly nice to keep engagement going. Kinda makes sense when you think about it that way.