Hey all, glad to be in here. I work on voice agents for lead capture and keep hitting the same questions this group talks about a lot: cost at scale, control over turn taking, and what it really takes to run LiveKit or Pipecat yourself. For anyone who moved a live client off a hosted platform onto a self-hosted stack, what ended up taking longer than you expected?

Here is the checklist I run before a voice agent takes live calls. 1. Call forwarding delay. Most phone systems wait 3 to 5 seconds before the forward kicks in. Call your own number after hours and count the rings. If it feels slow, fix it in the phone settings first. 2. Interruption test. Call the agent and talk over it on purpose. If it keeps talking for more than 2 seconds, tune the end of speech setting. Callers hate talking to a wall. 3. Booking path end to end. Give the agent a real slot and check the calendar after the call. No calendar event means no booking, no matter how good the call sounded. 4. Fallback when it fails. If the agent drops the call or mishears a number, a text should go out within a minute. A missed call answered by nothing is worse than a missed call. What else do you test before going live?

Been working with software systems for more than 10 years, mostly around backend, cloud, AI, automation, and product development. One thing I’ve learned, knowing a programming language alone usually isn’t enough. The harder part is understanding the actual business. How to automate work that’s still manual. Connect systems that don’t work well together. Build AI into real workflows. Keep the backend stable when usage grows. Deal with data scattered across different tools. These are the kinds of problems I’ve spent a lot of time working on here in Japan. But I’m curious about the US side. For people running companies in the US, what technical skills are becoming difficult to find? And what skills do you think companies will need more of over the next few years?

Hello. I am a full-stack developer specializing in AI automation, agent development, and model development. I am proficient in voice AI, various LLMs, and TTS development. In particular, I can handle the entire software development process, including Web3 integration, third-party API integration, AWS, and product launches. I possess significant experience in various specialized fields, such as internal API testing using SwaggerUI, web or mobile app version management via GitHub, and DNS. If my expertise aligns with your project, please feel free to contact me at any time.

I’ve a question. Mostly businesses don’t want to buy a twilio number for Voice Agents. They want to use their current/existing number. What’s the solution?