{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Build With AI","title":"# 164 How I Built an AI Voice Agent With Claude + Voiceflow (Zero Code)","html":"","width":"100%","height":180,"duration":3554,"description":"Build your voice agent in 10 minutes (No code required) \nhttps://corey-ganim.kit.com/18da152cf4 \n\nIn this episode, I sat down with Susan Westwater, co-founder of Pragmatic Digital and a conversational AI veteran since 2017, to build a working voice agent in Voiceflow live, with zero code. Susan walks through her exact prompt template for an appointment-scheduling agent, explains the difference between in-the-loop, on-the-loop, and fully autonomous agents, and shows how to separate your agent instructions from your knowledge base so you can update facts without breaking the whole build. We test the agent live (it called her cell phone mid-episode), connect it to a Google Sheet to capture customer intake, and talk about competitors like VAPI, ElevenLabs, and Voiceify. By the end, you'll have the exact playbook (and the template Susan is giving away) to spin up your own MVP voice agent in under an hour.\n\nTimestamps\n03:42 – Inside Voiceflow and what makes it different\n04:23 – Chatbot vs voice agent: listen, decide, act\n05:30 – In the loop vs on the loop vs fully autonomous\n09:09 – The system prompt: identity, purpose, and boundaries\n11:54 – Voice, persona, and speech sculpting\n13:22 – Separating agent instructions from knowledge base\n17:14 – Stopping the agent from troubleshooting electrical issues\n20:31 – Rules for collecting info one question at a time\n23:21 – Pasting the prompt and one-shotting the build\n26:34 – Voiceflow competitors: VAPI, ElevenLabs, Voiceify\n30:22 – Connecting tools at each conversation step\n33:13 – Why faster builds give up control\n38:21 – Adding the knowledge base as a Word doc\n43:13 – Sending customer intake to a Google Sheet\n45:57 – Live phone call with the voice agent\n50:09 – Branching, exit conditions, and iteration\n54:52 – Custom voices, ElevenLabs integration, and voice security\n\nKey Points\n\nKeep two documents separate: agent instructions (how the agent behaves, its identity, persona, escalation rules) and knowledge base (the facts...","thumbnail_url":"https://img.transistorcdn.com/fPP_LXbA6Rbv7hw4e1qgK-hy_oKL684f8rf7EF5X7TI/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS8zYWVm/NTk5YjU3OTk3NzAy/YzBlZDkzNzA0ZDIz/MjVjNC5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}