Hey everyone, I wanted to share a bit of my background and ask for some advice from people who are already running AI automation agencies. I’ve been working as a freelancer for a while, mainly building AI automations and voice agents. On Upwork I currently have a 100% Job Success Score with 5-star reviews, and most of my projects have involved building automation systems and AI-based solutions for clients. Recently I also started a YouTube channel where I showcase the systems I build (voice agents, automations, workflows, etc.) so people can see the actual implementations. Now I’m planning to start my AI automation agency next month. Initially, my main focus will be AI voice agents for clinics (AI receptionists, call handling, appointment booking, etc.), because it’s easy for businesses to understand the value. After that, I plan to gradually expand into other automation areas like lead generation systems, workflow automation, and content automation, since I also have experience with those. Right now my main questions are around pricing and infrastructure. Until now as a freelancer, I’ve always built systems directly on the client’s platforms (their Twilio, Vapi, OpenAI, etc.) and just charged a setup fee. But now that I’m moving toward an agency model, I’m wondering what the best approach is. A few things I’d really appreciate advice on: • Do you usually build on the client’s platforms or run everything on your own infrastructure? • For someone starting an agency, would you recommend continuing with client-owned accounts for the first few clients, or moving to agency-owned infrastructure from the start? • How do you typically structure pricing setup fee only, or setup + monthly maintenance/retainer? Another thing I’m unsure about is monthly maintenance. If I charge a monthly maintenance fee: - Is that something you keep indefinitely as long as the client stays? - Or do you structure it like a limited support period or contract (e.g., 3–6 months)?

Hi everyone, I'm trying to build an overflow handling assistant and I need help with Warm Transfer Experimental. What I'm trying to achieve: My assistant (Sienna) answers inbound calls, identifies the department, and transfers the call. If the department doesn't pick up within 15 seconds, I need the call to return back to Sienna automatically so she can take the caller's details. The whole thing needs to happen in one single call so the assistant retains the context of the conversation. What I've done: - Transfer mode set to Warm Transfer Experimental on all destinations - End call if transfer fails is unchecked - Summary generation disabled What's happening: The transfer fires correctly but after 15 seconds of no answer the call does not return back to the assistant. The call just dies. My question: Is Warm Transfer Experimental the right mode for this use case? And if so what exact settings are needed to make the call return to the assistant when no one answers? Has anyone successfully built this and can share their setup?

We're launching a $5000 Voice AI Hackathon, in partnership with the amazing team at Retell AI! This is a 7-day sprint to build voice agents that solve real business problems. What’s the point? → Build and demo a working AI voice agent using Retell's cutting-edge tech. → Compete for a $5,000 prize pool → Get hands-on experience building the next generation of voice AI. → Showcase your build to a community of agency owners, founders, and automators. This is for AI agency owners, automation builders, SaaS founders, and anyone excited about the future of voice AI. 🥇 1st Place: $1,000 cash + $1,000 in Retell credits 🥈 2nd Place: $500 cash + $750 in Retell credits 🥉 3rd Place: $250 cash + $500 in Retell credits 🏅 2 Honorable Mentions: $500 Retell credits each Want extra build support? Launchpad members get access to our dev team, reviews, and troubleshooting during the hackathon. The official kickoff is on February 25th @ 2PM EST. Launchpad members receive a 48-hour early build window starting February 23rd, with access to setup resources and dev support. To participate: Comment 'HACKATHON' I will send you the registration link via a direct message here.

Hey everyone, I’m building a live AI phone receptionist and I’m facing an issue when the assistant has to repeat numbers back to the caller. Problems: • When a caller gives an 11-digit phone number → digits merge or sound unclear • When repeating prices like £1500 → pronunciation sounds distorted • Works fine sometimes, but inconsistent on real phone calls Stack: Vapi + Twilio + n8n + ElevenLabs (also tested Gemini/OpenAI) Tried already : – Increasing end-of-turn timeout (0.5 → 2s) – Changing voices/models/LLMs How do you normally solve this in production systems? Is it formatting, TTS settings, buffering, or another approach?

A lot of people talk about “doing outbound consistently,” but what usually breaks isn’t effort it’s friction. Recently, I built a LinkedIn outreach system to remove that friction completely. What the system does: - Scrapes targeted LinkedIn leads - Researches each profile - Writes a personalized connection message per lead - Sends the connection request - Automatically sends the 1st and 2nd follow-up What this removes from the process: - Searching and opening profiles - Copy-pasting profile data - Writing messages one by one - Manually remembering and sending follow-ups Realistic time impact: ~20 minutes saved per lead. At ~30 leads/week → ~10 hours saved every week. The bigger outcome: Outbound runs in the background. Messages stay personalized.Follow-ups never fall through. If you’re curious and want to see the exact workflow or explore setting something similar up for yourself, feel free to DM me and we can walk through it on a quick call.