I’m currently working on an AI receptionist for HVAC companies (handling inbound calls + booking jobs). One issue I’m thinking about: 👉 How are you handling real-time interruptions during tool execution? Example: - Caller is speaking - AI is collecting details (name, issue, time) - Suddenly caller changes request or adds emergency info - Or interrupts mid-flow Right now I’m seeing cases where: - The conversation flow breaks - Or the tool gets triggered too early before full context is captured Curious how others are solving this: - Do you rely more on strict state management? - Or dynamic LLM re-evaluation after each turn? - Or interrupt handling at the voice layer (not model)? Would love to hear how you’re structuring this in production systems.

Building AI voice receptionist for HVAC (2-10 tech shops) — want builder input Building a 24/7 voice receptionist for small HVAC shops (owner-operator, 2-10 techs). Job: answer every call, book directly to calendar, route emergencies correctly, stay in lane on pricing/diagnosis. Currently on Retell AI + Cal.com, no CRM layer. Four things I want real experience on, not theory: 1. Feature list beyond booking — what's non-negotiable that I'm not thinking of? Reminder calls/texts before appointment? No-show follow-up? Anything you built that turned out to be the actual differentiator once live with a real client? 2. Follow-ups — is anyone running reminder/no-show sequences natively off Retell + Cal.com, or does that always require bolting on something else? At what point did you need it — client 1, or later? 3. Single Prompt vs Conversational Flow — for straightforward booking flows (not complex support), has anyone actually run both and compared? Where does Single Prompt start breaking down in practice, and at what call complexity? 4. CRM — running lean with just the calendar right now. What actually breaks without a CRM layer, and at what client count did you need one? What's the minimum viable setup people add first? Real numbers/experience over theory appreciated.

Hi, my name is Muhammad Ibrahim Jaffar and I have been in the voice AI space since before vapi existed. I was building my own voice AI at that time. Since then I have always been at the cutting edge of development. I haven't just used pipecat or livekit. I have hosted open source models on bare metal to get cost as low as 1 to 2 cents a minute with imperceptible latency. I have been trying to innovate in this space and bring something cool and exciting. Today I want to introduce you to a new frontier: Voice agentic UX Its when websites come alive controlled by an agent and the user interacts with the website using his voice (or text). The paradigm is supposed to bring about novel and curated audio visual experiences to market for the future of web. Where website does things for you and all you have to do is ask like you would a person and it holds your hands and guides you through it. Here is an early tech demo example for a car dealership: https://www.loom.com/share/ec77d88f685f4b399d9009ffeb35107f We are at the cusp of a new market and you are the only ones who have the chance to get ahead. Really excited what you think about this.

Hey everyone, I could really use some advice from people who have actually built and scaled AI agencies. My partner and I recently started an AI automation agency in India focused on real estate. We're both strong on the technical side and build custom AI systems ourselves. Our main offers are: - A WhatsApp AI agent that qualifies leads, answers property queries, recommends properties, and books site visits. - A complete AI agentic system with Voice AI for follow-ups, appointment scheduling, customer support, and other automations. We've tried a lot of local outreach, especially door-to-door visits, but the results have been disappointing. Most SMEs here either don't understand the value of AI yet or expect everything to be extremely cheap. I even tried lowering my price to just $50 for some offers, but that still didn't generate much interest. From what I know about international markets, these same solutions can easily sell for $1,000+ when positioned correctly. The good news is we aren't starting from zero: - We signed a large real estate client who's currently on a one-month free trial. - We're also in discussions with a quick-commerce company (through a referral) for a WhatsApp AI customer support system worth around $500 if the deal closes. The challenge is that I don't think staying focused only on the local market is the right long-term move. I want to start getting international clients. The problem is: - We have no budget for paid ads right now. - Door-to-door obviously isn't possible internationally. - I'm much stronger at building AI systems than I am at sales calls, and I'm not very confident on cold calls in English. - I do have experience with digital marketing, especially Meta ads, but that's not an option without a budget. So my question is: If you were starting from scratch today with solid technical skills but no ad budget, how would you land your first 5-10 international AI automation clients? Would you focus on cold email, LinkedIn, X, Loom videos, Upwork, partnerships, communities, content, or something else?

I have a warm roofing prospect asking detailed questions about WhatsApp automation. I don't have the technical implementation ready yet. I'm looking for someone who can build/deliver this with me. I'll handle sales and the client relationship. You handle the technical implementation. We split the revenue.