Hey Folks, Does anyone have the call Scoring System after the call finished or anybody working with that? Appreciate your help! I'll be making one for scoring the call based on the length, activity and Output! Need suggestions

If you’re still copying and pasting parts of your prompts (or full prompts) between assistants… there’s a simpler way to do it. Yes, we can just copy the assistant ID or duplicate the assistant for the full setup. Most people completely miss this, but custom snippets are the simple solution. Instead of rebuilding prompts or digging through old ones every time, just save the parts you reuse. Stuff like tone, personality, structure, tasks, booking process, after hours, spam & scam protection, off-topic conversation handling, etc… Snippets let you separate all that so you can plug things in without starting over every time. Think of your prompt like different sections that make the entire prompt. Save each one once, and now you’ve got building blocks instead of one giant prompt. Quick tip too, name your snippets clearly. Even better if you use emojis so you can spot them instantly without opening each one. And this isn’t just for prompts. Same idea applies to your GHL SMS & Email snippets… if you’re writing something more than once, turn it into a snippet. Once you start doing this, everything gets faster, cleaner, and way more consistent.

Most conversations about Voice AI agency ops focus on: how do I build better agents? I’ve started thinking that’s the wrong question — at least past a certain point. Once you have paying clients and real deployments, the question that actually determines whether you keep those clients isn’t “how good is my agent” — it’s “how quickly do I know when something isn’t right, and can I prove the agent is working before anyone has to ask?” Building better agents doesn’t help you if your client finds out about a failure before you do. And it doesn’t help you if there’s no automatic proof of value being delivered between build and renewal. I’m not saying quality doesn’t matter. It obviously does. But I’ve seen good agents lose clients — and mediocre agents retain them — based entirely on whether the operator was on top of what was happening operationally. Am I off base here or does this match what others are seeing?

I find this has been happening a few times. It's like when the assistant gets stuck at a tool call, it just goes silent and stops responding. How can I fix this or have a fallback? Call Id example: call_f7d72c7b-23c1-499d-bf0d-58eb5fc5adea

Our AI voice agent is really struggling with phone numbers and email addresses. When it reads them back, it comes out as garbled nonsense rather than clearly spoken digits or spelled-out characters. Same issue both ways — it either skips letters, adds strange sounds, or just sounds completely unintelligible. Has anyone run into this and found a fix? Prompt-level solution, pre-processing the input, or something else? Would love to hear what worked.