@@theibrahimmunir 🤣I have my flow set up to send emailed reports instead of going to google sheets and I'm getting like 60 duplicate emails per call....any idea why?
@@mikefetherling Lol that's strange -- the best that I can think of is that maybe somehow your automation is iterating 60 times instead of sleeping 60 seconds? Double check the sleep module. If that's not the issue, you can always email me at ibrahim@shadow-ai.co with more details/pictures if you'd like since it might be a little bit hard to pinpoint the exact issue without a closer look
@@theibrahimmunir Thanks so much for your reply! I think I had too many items selected under Server Messages in the Vapi Dashboard. I had function calls, hang, and status update selected which I think kept creating new messages. Going back and closely following what you did solved it.
Hey Moben, you can grab the API key by logging into your VAPI Dashboard, click on your email at the bottom left, then click "API Keys". Copy the private key, and then under the header, the name should be "Authorization" and the Value should be "Bearer PASTE_API_KEY_HERE" Hope this helps.
I have a problem, if I run the script once it doesn't collect the data, and if I leave it running it works non-stop and collects the data, it fills the table as it should, but it costs me 3000 operations in Make. What should i do? And the most important question, if the agent receives 5 calls and the scenario in make is started once, should the scenario collect the data of all 5 calls?
Hello Dusan, I don't think I fully understand. If the scenario has 5 modules, then it should consume 5 ops on each run. 3000 ops means you might be doing a lot of calls in bulk. For the last question, make sure the scheduling is set to "on demand" and is the scenario is turned on. That way, it will run 5 times for 5 calls, which is how it should be. Hope this helps.
Are you referring to the old/standard way of using GPT in something like Make to do summarization/data extraction, etc? If so, yes, these call reports pretty much replace that old way. Let me know if that helps and if I understood the standard function correctly
@@theibrahimmunir Yes that's exactly what i am talking about! I'll give it a go and try testing it out. Regardless, you are a life saver thank you so much!
This is VERY helpful - thanks for taking the time to post this.
Of course, thanks for watching!
@@theibrahimmunir 🤣I have my flow set up to send emailed reports instead of going to google sheets and I'm getting like 60 duplicate emails per call....any idea why?
@@mikefetherling Lol that's strange -- the best that I can think of is that maybe somehow your automation is iterating 60 times instead of sleeping 60 seconds? Double check the sleep module. If that's not the issue, you can always email me at ibrahim@shadow-ai.co with more details/pictures if you'd like since it might be a little bit hard to pinpoint the exact issue without a closer look
@@theibrahimmunir Thanks so much for your reply! I think I had too many items selected under Server Messages in the Vapi Dashboard. I had function calls, hang, and status update selected which I think kept creating new messages. Going back and closely following what you did solved it.
@@mikefetherling No problem! Feel free to reach out if you have any more questions.
Thank you for the detailed video!
Of course, thanks for watching Rick!
Great video, helped a lot!
Thanks Henko!
This was Super helpful
Appreciate it Shaz!
Nice video
Thanks! Let me know if you have any questions or topics you'd like me to cover for future videos
Great video, quick question where am I getting the API key and bearer token for the http request? Is this from my Vapi API?
Hey Moben, you can grab the API key by logging into your VAPI Dashboard, click on your email at the bottom left, then click "API Keys". Copy the private key, and then under the header, the name should be "Authorization" and the Value should be "Bearer PASTE_API_KEY_HERE"
Hope this helps.
I have a problem, if I run the script once it doesn't collect the data, and if I leave it running it works non-stop and collects the data, it fills the table as it should, but it costs me 3000 operations in Make. What should i do? And the most important question, if the agent receives 5 calls and the scenario in make is started once, should the scenario collect the data of all 5 calls?
Hello Dusan, I don't think I fully understand. If the scenario has 5 modules, then it should consume 5 ops on each run. 3000 ops means you might be doing a lot of calls in bulk.
For the last question, make sure the scheduling is set to "on demand" and is the scenario is turned on. That way, it will run 5 times for 5 calls, which is how it should be.
Hope this helps.
Correct me if i'm wrong, we can use this instead of the standard "function" to get the necessary data right?
Are you referring to the old/standard way of using GPT in something like Make to do summarization/data extraction, etc? If so, yes, these call reports pretty much replace that old way.
Let me know if that helps and if I understood the standard function correctly
@@theibrahimmunir Yes that's exactly what i am talking about! I'll give it a go and try testing it out. Regardless, you are a life saver thank you so much!
@@abhinavmukala6083 Yes, it should be a lot more easier then (VAPI does it all under the hood so you don't have to worry about it)!
can speak over use tool de vapi
Sure, I can do a video on tools. Thanks for the feedback!