- Problem: My Retell AI agent books appointments via Cal.com API. Only the admin (calendar owner) gets booking notifications, but the customer gets nothing. Plus the email field in Cal.com is empty - only shows first name. - Current Flow: Retell call → captures customer email as dynamic variable → books on Cal.com → logs to Google Sheets → only admin gets notified - The Issue: I don’t think Retell is passing the email dynamic variable from the batch call/Google Sheets back to Cal.com during booking. The Cal.com booking only shows the customer’s first name, email field is empty. - Need: Customer confirmation emails and reminders using the email captured in Retell dynamic variables/batch calls and logged in Google Sheets. - Questions: 1. How to pass email dynamic variable from Retell/Google Sheets to Cal.com during booking? 2. Should I trigger customer emails separately through n8n using the Google Sheets data? 3. Best way to handle reminder sequences when Cal.com doesn’t have the customer email? - Tech Stack: Retell (dynamic variables), Cal.com API, Google Sheets, n8n, Gmail Anyone solved this before? Looking to improve appointment show-up rates. Thanks!

Hey guys, I need support here, I have a client at $1500 a month that wanted a 6 month agreement, and originally agreed was: ✅ AI Recruiting Phone Agent – Calls, qualifies, and follows up with recruits via text & email ✅ AI Digital Twin (Tavus) – Personalized video messages for lead generation, onboarding, and real-time Q&A ✅ AI Recruiting Website – High-converting site with a built-in AI chatbot (and voice agent) to engage potential agents We first started on the listing agent but he said he didnt have the bandwidth to actually be selling houses so he wanted to focus on the recruiting phone agent. We cloned his voice which took 2 months of recording over & over with some breaks on his part, but now he also wants the agent for outbound calls to call homeowners that want to sell which he originally reached out about. At $1500 per month on top of custom coding his website in react and doing the digital twin cloning, voice cloning with elevenlabs that took 2 months to finally get it at a level... is like... okay still fine-tuning the recruiting agent prompt engineering. I tried to do the DesignJoy business model of subscription and build new requests for $1,500/month one at a time, but the extensive testing of the first agent on top of everything is a lot :/ Should I ask for at least $500 upfront invoice for second agent? 3 months left of the 6 month agreement. ------------- Context of where we're at: The full-stack website development is fully complete with cal.com calendar booking widget. ElevenLabs voice agent is live and will be calendar-connected soon. Digital twin real-time video calls are also live on the site. Currently setting up Twilio for SMS that will forward directly to him. Seems like despite all the work that is shown after him being okay with it taking time before the agent is perfected for calling, today he said he wants recruiting and listing calls (2 different agents) making calls at a functional level ASAP, but I’m currently having prompt engineering issues with the agent reading the whole script nonstop when the human responds 1 time with confirming their name. So that’s taking more days. I put <wait for response> & it still reads entire wording without their response at every section.

OpenAI just dropped a brand-new lineup of AI models—and they look like a game-changer for building AI agents. They're faster, smarter, and more affordable. In this video, we’re digging into what it actually means for chat and voice agents—and whether the new models are just hype or a full-on upgrade in every category.

Hey everyone! 👋 I'm building a mental health phone agent with Vapi that needs to collect specific data points (name, DOB, responses to 12 screening questions, notes) and send them to AWS DynamoDB. What's the best approach to capture this structured data from the conversation? Should I: 1. Set up explicit variables in the Vapi agent for each data point? 2. Parse the conversation transcript after the call ends? 3. Use a combination of both approaches? I know Vapi can send webhooks to AWS, but I'm trying to figure out the cleanest way to extract the specific data points from the conversation flow. The agent follows a specific script with clear questions, but I want to make sure I'm reliably capturing the responses. Also, which transcriber (STT) do you recommend using on Vapi between OpenAI Whisper, ElevenLabs, or Deepgram? I need accurate transcription for mental health conversations and accurate patient responses. Has anyone implemented something similar or have recommendations on the best practices? Thanks in advance!

Skool has just released a new map feature, and I've enabled it for the community. It’s great to see where everyone is; there are so many different places! Make sure to have your location set on your profile to show up. https://www.skool.com/brendan/-/map