Is there a way to trigger an outbound SMS through GHL to send out the initial SMS message and have it be unique to the contact every time? Or does the first message have to be the send sms action from GHL and then the assistant engages on response?

Is email available yet as a reply channel with the AI?

Hey everyone! 👋 Wanted to pop in and make my first post here. I'm Halie — I've been working with the Assistable team as a beta cloud employee. I'll be hanging around the Skool group and DMs pretty regularly, so if you ever need anything just tag me or shoot me a message. Quick background on me: I have access across all departments, vendor Slack channels, and the Assistable platform itself (browser + API), so I can jump in and help triage things when needed. Since I'm here, figured I'd share a few updates: Webhook fix — Yesterday some of you may have noticed webhooks not firing. We tracked it down to a recently configured webhook that got stuck in a retry loop and was hogging server bandwidth. Found it, patched it, should be good now. New system prompt — This is a big one. We updated the core system prompt for the first time in a really long time, and the beta tester feedback has been super positive. It's one of the most comprehensive agent wrappers we've built — proper date/time context, user context, cached memory across channels, and stylistic tuning that keeps your agents sounding natural instead of robotic. Along with that, here's the updated variable set which covers a wide range of date and time variables for all use cases: https://docs.google.com/document/d/1pH_gk89wUf0dSjx0wLlJKgFVYt9yPNgwLrgtFbu4TXs/edit?usp=sharing STT update — We're rolling back from Deepgram Nova 3 to Nova 2 for now to cover a wider range of languages. But good news — with the V3 front end launch, you'll be able to pick your STT provider yourself (Nova 2, Nova 3, Flux from Deepgram). And for the multi-lingual folks, we're adding Krisp AI as an audio passthrough for noise reduction and cleaner transcription. V3 front end — Took a peek at the latest GitHub repo and we're getting really close to pushing this out. It's a big step up in stability — agent orchestration, load times, run times, the whole experience gets a lot smoother.

Major changes in functionality, accessibility in chat and voice tool call logs include inputs, outputs and more. There updates makes multi-calendar, multi-timezone booking native along with some other cool stuff. Direct accounts get first access to tools v2 including the revamped make ai call, send email & self scheduling, as well as the new tool sets search the web, get sheet, get doc, update appointment details and more. ChangeLog: - Check availability, book appointment, reschedule appointment, cancel appointment, and check appointments have now become -> Check availability, book appointment, update appointment details and get user calendar events. This allows the bot to do some new cool things like multi-calendar book from just the prompt alone, dynamically change the timezone of the requests for multi-timezone bookings and more. - Update details and update address has now become -> Update User Details which now updates every GHL field besides tags and custom fields (these are other tools). So changing timezone, address, name, contact info, etc is all accessible by the AI now. - Send email has been audited and recreated with fallbacks and information protocol so the AI will know to collect an email before sending the email and understand whether the send was successful to the email (to re-collect it). - Self-schedule has been audited and recreated to... well self schedule. The schedules will be editable, cancelable and viewable in the AI portal in the sub-account. New Tools: - Get Sheet -> gets information from a google sheet and returns it to the AI - prompt-able URL inputs. - Get Doc -> gets information from a Google Doc and returns it to the AI - prompt-able URL inputs. - Search the web -> searches the web and returns the results to the AI to use for conversation, research or more. --- These will all be released in a bit into production for both chat and voice and accessible via the tool menu under tools v2 for direct users only -- resold users will get access at a later date once resellers have been briefed and given documentation.

Our full assistant / agent infrastructure now support local variables (our variables) AND custom fields AND values in the prompt for chat (SMS, instagram, Fb, whatsapp, etc), inbound calling and outbound calling. make sure to reference your variables in the prompt as closed, no-space brackets. Example: - {{custom_values.my_booking_link}} - {{contact.last_call_summary}} ...etc. This means you can now -- with the power of tools and the power of the native variables now -- build dynamic assistant just with variables as prompts -- super cool if ya ask me happy friday