I’ve recently deployed an AI receptionist (“Ellie”) for a local company to handle after-hours calls. During the day, they’re still on RingCentral, but the long-term vision is to replace RingCentral altogether and let the AI system handle calls 24/7. For now, the idea is to give customers an immediate engagement opportunity rather than just hitting voicemail after hours. Here’s what I’m seeing so far: Some callers are caught off guard when they realize they’re talking to AI, and they hang up or ask for a human. So I’ve set Ellie to capture the basics (name/number/reason) and kick out a callback request when that happens so no warm lead is lost. The owner is okay with her handling a few more calls before deciding, but he is talking of re-evaluating the whole thing. I’m considering making Ellie more transparent upfront, e.g.: “Hi, this is Ellie, your after-hours virtual receptionist for [Company Name]. I’m here to make sure you’re taken care of right away—whether that’s scheduling a visit or passing your message to the team first thing tomorrow.” You get the picture. I’m also thinking about updating the website/Google profile to set expectations that after-hours calls go to a virtual receptionist. Has anyone else run into this adoption hurdle? How have you “sold” the idea to both business owners and customers so it feels like an upgrade instead of a surprise? Like an enhancement. Would love to hear how others are framing and rolling out AI receptionists in similar situations. THX!

With GHL announcing their own MCP server is there a use case we could use that would allow us to make our Assistable agents able to do more in the system. https://share.descript.com/view/Vh4KL20TzzN

What a wild ride all of this has been. 2 years we've been around now. This all started because I ran an agency after quitting corporate America and needed a white labeled chatbot builder. we've had many up & many downs. The W's keep flying and we persist through the rest because of an amazing community and a platform built for the people using it; by the people using it. 2 years later, our builder has changed a bit and the same faces are still around to see it. We've stepped into a stage where we are outgrowing some of the vendors and platforms we were built upon -- we never want you to experience that so we continue to innovate. Last friday, we had one last problem with a vendor that was a final straw for us coupled with some other things. I'll be releasing version 3 early which is an independence update. We are moving our frontend to our own custom code to match our full enterprise backend to make yours, and your clients, experience much better. Along with that, we will have some independence from 3rd party platforms like OpenAI with optionality to use our in-house LLM specifically trained on casual language and appointment booking (with NLP training for both chat and voice cadences). Couple with this, a couple of other things should come with it: - Flowbuilder production v1.0.0 - conversational pathways with determistic tool calling so you never have to worry about objectives being missed. This introduced global nodes, forced tooling and light weight nodes for a fast and no-hullicnation AI - new front end - we've be oauthing to the new front end so you can acutally choose hwich one you want until legacy gets deprecated - more fallbacks - we'll balance everything all natively and in 3 databases (google cloud, aws, and cloudflare) so we can be 'always up' even if the front end isnt - focus on inhouse telephony solutions - number anayltics, a warming network amoungst users (platform numbers will call platform numbers to keep each other warm) and inhouse verification - all compliance - hipaa gdpr soc2 etcetc - ...tons more

Hey quick question, is it possible to send the transcription of a call via a GHL Automation to the client directly ? Or do I need to use the custom tools and extraction tool to make it work ?

hey yall, long time no talk. I wanted to get on my soap box to talk about some things... its 10~ mins if you could spare me that in the background :)