Have any questions? Text me (iMessages & SMS): 770-296-7271 Need white-gloved help RN? (I am in there too): help.assistable.ai Have anymore questions? Text me and I will make a video over: 770-296-7271 ----- where have i been? - Actively trying to fire myself. I think a long term worry internally, myself, and from the community is key man risk. My only objective is trying to make sure this outlives me. Im mad. - Me too. Lets figure it out together, reach me or team and lets make sure clients are super duper happy Why is X happening? - I explained in the vid along with solution - if you are super busy, text me and ill get you an answer in less than 5 mins What can I expect? - A platform that does rely on me or any vendors - something that we own in entirety and can be maintained by people much smarter than me X ? - Y A (aka text me or run it up to support and they will send to me) we are on call 24/7, ask anyone thats talked to me in the past week - I have slept collectively 6 hrs (not even in my bed :/ ), yelled at some people upstream, and gave every ounce of my time to help anyone down stream I miss making videos and being involved here. I want to do it more. Thats what we are trying to do here

So, its been a long process and a lot of work - literally re-writing our voice orchestration to be native - and we still have a small sprint before we will start flowing traffic that way. Here is just a general guide of somethings that will change, be added and be deprecated. So, rollout. first - the users using our numbers will start seeing the traffic flow first. Then older numbers. Then trunked numbers. Nothing tangible changes from your perspective besides lower latency. Tooling - So, we are adding POST / GET / PUT / PATCH / DELETE to api request types. We also have it where you can configure headers, query parameters, path parameters and body parameters. So, fully customized API calls. We will suppose variables in these as well so you can pass API keys or your access token for GHL. Here's the thing, tools is now running through a proxy of ours that will open up the doors for a couple things: - Tools to run as they do today - Direct API calls (will be a toggle), so instead of being wrapped in a args object with metadata, etc - we will just send the API call. This gets rid of the need for middleware because you can make direct API calls. - Workflow execution; not today or the next week but we are adding native workflows to the platform. You can configure a custom tool to trigger a workflow locally to run multi-agent frameworks and basic automation so we will support a middleware internally. Abilities - all stays the same, but we are adding agent teams in voice (chat following right after). So, add different assistants into call to create a team env on the call either through a "prompt change" so we just change the prompt dynamically, or through a team so mutliple voices, etc. AI Models - We will be running a custom fine-tuned model thats been fine-tuned for voice orchestration. aka, this llm outputs text-to-speech friendly output to keep weird translations to a minimum. You will be able to select an OpenAI model if you would like and run it with your key if you prefer OpenAI output.

Would yall want to pass your own 11labs key for your own voices / acct for voice? would obviously drop price for input keys but curious would anyone use this before I built it / move on

Thinking about dropping a little GPT that will help refine your prompts...drop a 🔥 if you want access No strings attached, it'll be free.

So, last friday on the Friday founders call (you should so totally join in) -- we built a BAD ASS self selling demo that dynamically changes it's own prompt to actually generate a prompt for the user, demo it to them, and save it to use later (I added a lot of functionality to it) This is a comprehensive self-selling demo :) I will release the snapshot and the accompanying video later today