I'm sure there are research demos in big companies, I'm sure some AI bro has done this with the Twilio API, but no one is seriously doing this.
All it takes is one "can you take this to the post office", the simplest, of requests, and you're in a dead end of at best refusal, but more likely role-play.
What does work in production (at least for SMB/customer-support style calls) is making the problem less magical: 1) narrow domain + explicit capabilities (book/reschedule/cancel, take a message, basic FAQs) 2) strict tool whitelist + typed schemas + confirmations for side effects 3) robust out-of-scope detection + graceful handoff (“I can’t do that, but I can X/Y/Z”) 4) real logs + eval/test harnesses so regressions get caught
Once you do that, you can get genuinely useful outcomes without the role-play traps you’re describing.
We’ve been building this at eboo.ai (voice agents for businesses). If you’re curious, happy to share the guardrails/eval setup we’ve found most effective.
is obviously a staged demo but it seems pretty serious for him. He's wearing a suit and everything!
https://www.instagram.com/p/DK8fmYzpE1E/
seems like research by some dude (no disrespect, he doesn't seems like he's at big company though).
https://www.instagram.com/p/DH6EaACR5-f/
could be astroturf, but seems maybe a little bit serious.