Each tier in assistable shows that we can provide our own keys to models. Has anyone done this yet? I dont see any messages here in skool about it when i searched. Im wanting to run some tests using local model(s) Here's what im talking about

I wanted to share a small but powerful tip that can make a big difference in how your AI assistant sounds. When we troubleshoot voice interactions, one common issue is that the AI can sound flat or robotic. The fix is often not in the software itself, but in how the prompt is written especially the punctuation. - Periods (.) and Commas (,)These act as natural pauses. They keep the assistant’s replies flowing smoothly. - Ellipses (…) and Dashes (—)These add subtle hesitations or transitions, almost like the AI is “thinking.” By mixing both styles, you can guide the rhythm of the response and make the AI sound much more natural in conversation. I picked up this little trick from Jorden and it’s been super helpful, so thought I’d share here. Curious to hear if others in the community have tried similar tricks.

Want a GitHub repo’s content in your AI knowledge base? I’ve used several tools in the “website to markdown” space, I still find jina's solution to be the most impressive. However, gitingest is designed specifically for working with GitHub repositories and has some badass features therein. Side note: For those not familiar with GitHub, it's worth exploring even if you're not a developer. The platform offers valuable resources and tools that can benefit people across different disciplines - many aspects of software development have applications beyond pure coding. Check out the octoverse lol This tool allows you to easily extract content from GitHub repositories and save it either as files or to your clipboard, making it perfect for creating knowledge base content in Assistable. Link: https://gitingest.com/

I’ve been experimenting with prompt formats and was curious about something. Instead of writing prompts in plain text, has anyone here tried structuring them in JSON format? For example, using keys and values to organize context, instructions, and expected outputs. If you’ve tested this, how did it compare? Did you notice clearer results, different behavior, or weaker performance? Would love to hear your experiences, whether it worked better, worse, or simply different.

Hi everyone, I just read a LinkedIn post where someone lost $20K in minutes because their Voice AI callback form was hit with fake international numbers. Their agent kept calling and talking, draining their balance completely. This is a wake-up call for us. We should make sure we’re fully covered against something like this — things like CAPTCHA, spend caps, geo locks, concurrency limits, etc. I wanted to bring this up here so we can make sure we’re all covered and avoid any risks like that and protect ourselves and our clients. Better safe than sorry. 🙃 We’ve seen a few of our clients go through this too, and it can get really messy really fast. That’s why I think it’s important we put the right safeguards in place together. 🙌 @Assistable Team @Mike Copeland @Jorden Williams