I’m making a quick tool for myself to help me organize receipts. I have created the webhook which is sending the correct data i want. But i got stuck a bit. I am trying to send the data to a google spreadsheet. The major fields is no issue like: date, vendor, amount tax.. There is a field called: line item that im having issues with. I would like to list all the item in the same cell but for some reason it only lists the first item. As you see in the first photo the package arrives corretly, the lineitems are in a bundle with numbers. When im trying to map these in the spreadsheet it doesnt let me do it. Only allows me to do one. And lists the first item only. The best would be if i could put all the line items into one cell nicely under each other lol. Would anyone be able to point me to the right direction please? @Alejo Pijuan @Tylan Miller 🙏🏻

We just wrapped up another dynamic Build Hours session filled with practical problem-solving and valuable insights. For those who couldn't make it, here's what you missed: 🤠 Assistant Connection Troubleshooting: @Lisa Grace brought a challenging issue where her VAPI assistant wasn't connecting properly. Through live debugging, we: - Examined the Make automation and webhook configurations - Identified an "Invalid Assistant" error in the webhook response - Validated JSON formatting using JSONLint - Discovered potential issues with repurposed VAPI organizations and Make connections This was a great example of systematic troubleshooting approach for voice AI implementations. 💥 VAPI Squad Transfer Deep Dive: @Jason Smith shared an interesting challenge with squad transfers - when adding an external phone number transfer option, the AI started explicitly announcing transfers even between squad members using the same voice. The group explored potential solutions including modifying transfer messages and investigating the transfer call function configuration. 💰Pricing Strategies for AI Voice Solutions: @Zoltan Nagy sparked an enlightening discussion about pricing voice AI solutions. Key takeaways: - Starting price point: $1500-2000 for basic call handling - Add 50% buffer to estimated development time for unexpected challenges - Monthly pricing strategy: Consider bundling setup costs into higher monthly fees (e.g., $600/month) instead of large upfront costs - Include minutes, maintenance, and technology updates in monthly fees ☎️ Twilio A2P Compliance Deep Dive: @Tylan Miller provided expert insights on A2P registration: - A2P registration is mandatory for texting U.S. numbers - The process can take about a week - Registration costs money per campaign attempt - It's a carrier-level requirement (Verizon, AT&T, etc.) - Having your own Twilio account gives more control vs. using platforms

We're back to Building tonight! 🚀 All members are welcome to join us for Community Build Hours, a supportive space for any and all kinds of questions. Whether you're using make, Vapi, the API, or another platform to build and deploy your solutions, Build Hours is here to help everyone build better and faster. Bring your questions and your builds as we leverage the expertise of Amplify Voice and the community to help you get unstuck and to facilitate your next AHA moment. JOIN HERE at 9:00PM EST!!! 🔥🔥https://us06web.zoom.us/j/81878562225?pwd=Aq0jxQYWxpIblgLKZ5Hq7a2KJfqcRP.1🔥🔥 Not building? No problem! Build Hours is a great place to learn even if you're not actively building. Maybe you have more of a background in sales and marketing but want to understand Voice Agents on a deeper level... come to Build Hours! ALL ARE WELCOME! Good Vibes Inevitable! 💫 See you TONIGHT!

Hi guys, Im building an AI receptionist that is meant to handle missed calls during after-hours and answer common customer questions. As many businesses (I assume) get the same common X questions all the time, I have tried to put together a KB. It turned out that my business has about 5 different "areas" that have its own separate Q&As. My thinking process was the following: Putting everything into one prompt is going to cause latency and makes it really hard to update. I have decided to create 5 different KB documents and prompted the AI to use each KB based on the questions the caller asks. So now the latency is good, no big issues there, but now the AI is hallucinating a lot or using answers from the appropriate KB but only some. Some answers are clearly in the KB yet it says doesnt have answer for it. I might have to mention that I sent the KB through chat GPT and asked it to convert to an easy-to-follow format for the voice assistant. Do you have any helpful tips for me on how to handle this?

Message us if you’re in Miami! 🏝️ we’ll see you next week for Tuesday Build Hours at 9:30am EST💪