📄 Documentation & Supplemental Learning: https://docs.google.com/document/d/1HbhCZHxbl-tfAXueC1XtjoFG0naJbW3nx36hDFbmaIQ/edit?usp=sharing ➤ I have been personally going through custom tools lately that are not able to be mapped or having trouble will calling the tool so I created this 20 min crash course that goes over everything exactly and I build, test and use an update_contact custom tool to show you how to map it ➤ Some things I have noticed: - Custom tool names and parameter names should be in JSON format: All names should be completely lowercase with underscores instead of spaces, with no special characters. Simple raw text with underscores. (I.e. update_contact, send_sms, first_name, opt_out, etc) This makes mapping consistent and reliable since args is completely AI generated and LLMs are familiar with JSON formatting. - Descriptions are so very important. AIs are smart - but that are not super intuitive. So, your description is key. It should leave absolutely nothing to interpretation. Be clear and concise on what the tool does and under what condition to call the tool - this create a consistent and reliable rule for functionality that the AI can understand. This goes for both the tool description it self and the information. ____________ ➤ Leave no room for AI interpretation on what the tool does, what you want it to do & when you want it do Examples of great descriptions: For a tool itself - Get the delivery date for a customer's order. Call this whenever you need to know the delivery date, for example when a customer asks 'Where is my package' For a parameter - The annualized revenue of the user in raw number format. For parameters, we leave no room for interpretation on what information we need, and in what format to send that information. ⛔ opt_out: contact opt out The reason this is not great is, opt out of what? what format - true/false, yes/no? etc. There is a lot of room for interpretation and inconsistent results may generate (args is generated by AI)

I set up SIP thinking I could use the same number for both texting and calling. However, I quickly realized that in Assistable, you can’t assign both a text bot and a voice bot to the same phone number. This limitation made my initial setup feel a bit pointless. To simplify, I think it’s better to set up a voice bot on a dedicated Assistable-purchased number, then forward calls from my texting (LC) number to this voice number. This setup isn’t a single, unified phone number, but it’s straightforward and sidesteps the restriction where each bot (voice or text) requires its own unique number. Ideally, if we could change the caller ID on the Assistable voice number to match the LC texting number, it would make the whole experience feel seamless—one number for both calling and texting. Does this logic make sense, or am I missing anything?

Hey hey assistacrats 💙 Its been a long time no talk - v2.1 was suppose to come out Friday but I got some ideas from those who I have been asking for feedback, watching the skool and looking at trends in support tickets submitted / calls Scale. <- thats what this update is, I dont really want to have to touch the platform on a daily basis - we needed for safety rails, archiving > deleting so you can recover deleted assets, multi-workspace for those who have multiple agency or require some from clients & reseller, rebilling via per-per-use, tooltips and tutorials (education and help) I would rather be interacting with the community. Having the weekly calls. Posting videos. Working hands on - this is the first step in that direction. Info on Pay-Per-Use: - When this goes live, accounts in negative mins with be set to 0 and accounts with their rebilling plans active will begin to get credited their call mins. accounts without a plan, calls are credited to you as a agency. All of which will be processed on the first of the month at price-per-min x mins - you will have the hard set limits if you prefer to not rebill the client Info on multi-workspace: - When this goes live, you can have as many workspaces as you would like for whatever reason - all workspace will require a plan. This does two things: 1. sets the price floor for resellers 2. allows users to deploy to clients outside of their GHL (AI automation agency model) will have more to come, after this update - we are resources only for a while, no new features, no changes to features because our focus is scaling together with you so with all of that, ill begin to start deploying those changes today and continue building until the final release is out - then we are in resources -- Those who have reached out, getting back and catching up today

How can we share recent chat history across different communication channels like Facebook, SMS, or phone calls? Is there a built-in feature in Assistable or a custom tool needed to ensure continuity in conversations? If anyone has experience with this or knows if it was implemented by @Jorden Williams, please share your insights or any helpful resources. Thanks also @Jason Dueck @Jakin Harper @Esteban Lopez @Justin Lee for any input. :)

im taking a quick break but I have to ask just in pure curiosity and feature building - is the chat widget in super demand? Why so with options available - what do they lack? Is this for support, sales, or general chat/faq? do you need something robust / flashy (like intercom - and if so why not intercom)? or just simply does its job (aka chatting with a widget w/ proper functions)? super curious to hear more on this