Over the weekend, we rolled out a new chain-of-thought processing feature that showed a lot of promise during testing( In an effort to make AI smarter) While it worked well in most cases, a few unexpected bugs popped up in live environments. Out of an abundance of caution, we’ve temporarily reverted this update to ensure stability for everyone. This change does not affect the recent improvements to the update_user_details tool — those are still live and working great. Thanks so much for your understanding while we fine-tune things behind the scenes. We’ll keep you posted when the enhanced version is ready for prime time! 💪

The assistant (voice) is repeating itself and speaking out some of the instructions in the prompt. For example, "Got it — thanks. Can I get an email next?Thanks — Johnny. Can I get your email address?" and "I’m sorry that happened — I can help. A bike accident falls within our practice areas. Can I get the date the crash happened? (One clear question at a time.)" and Agent: Got it — I'll save your contact info and continue with scheduling.Thanks, John — I’ve saved your contact info. What city do you live in?(Reminder: ask one question at a time.) What city do you live in?I'm ChatGPT supposed to respond as Sara. Need to ask city. Keep one question.What city do you live in? -------------------------------------------------------------------------------- Anyone else experiencing this, and is there a fix that you know of? I've even tested Assistants that have been working well, and it is the same with those.

I'm curious as to when we are going to get backend access as a reseller to API's for things like creating and assigning phone#, billing, adding active tags to assistants, rebilling errors, upgrading accounts, and more? I feel like we are miles behind everyone else when it comes to these things. This is a big scalability issue.

When are we getting a usable API to this? Or is that not ever happening? GPT is gonna smoke this if this doesn't learn to become less dependent on GHL. GHL has their own AI (which is terrible), but all they will have to do is tweak a few things. Tying your whole business to GHL then basically tying all your users to GHL is crazy. Being an independent platform with a GHL connection makes way more business sense.

Has anyone figured out a way to fully stop audible narration? I'm still getting completely random narration of internal processes like "Storing the user's full name as..." or "Saving address as...", etc. It's not all at once, and it's not always the same thing. The issue is that it changes depending on how the conversation is going. So, sometimes it will narrate a tool and nothing else. Other times it will narrate an internal process and not the tool calls. Sometimes I'll test a call both on Voice Lab + using the phone number and it will work smoothly. I'll leave it for a few days and the narrations come back. Is this due to updates? I can't pinpoint it and I've tried a ton of prompt variations. Things I've tried so far: - Added [brackets] around internal tasks like tool calls - Explicitly stated in the ## Style Guardrails to: - Never refer to the caller as user or narrate (e.g. user is reporting an issue with...) - Never announce the use of any tool (e.g. storing the full Name as, Storing Phone as) - Never announce any internal process (e.g. starting to gather details; starting to assist) - Upgraded from GPT Mini -> GPT 4o -> GPT 4.1 Not really sure what else to do. I know others have mentioned this issue so I'm curious if there are any solid solutions in place.