# From Prototype to Production: How Perk Built a Voice AI Agent That Makes 10,000 Calls a Week

Page: https://stenobird.com/podcast/just-now-possible-7481489/from-prototype-to-production-how-perk-built-a-voice-ai-agent-that-makes-10-000-calls-a-week
Text version: https://stenobird.com/podcast/just-now-possible-7481489/from-prototype-to-production-how-perk-built-a-voice-ai-agent-that-makes-10-000-calls-a-week.md
Podcast: [Just Now Possible](https://stenobird.com/podcast/just-now-possible-7481489)
Published: 2025-12-04T09:00:00+00:00
Episode link: https://justnowpossible.podigee.io/12-a-voice-ai-agent-that-makes-10-000-calls-a-week
Audio file: https://audio.podigee-cdn.net/2232610-m-3ab8db3949fd66a8a9b41b97334b8cb5.mp3?source=feed
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/just-now-possible-7481489/episodes/from-prototype-to-production-how-perk-built-a-voice-ai-agent-that-makes-10-000-calls-a-week
Duration seconds: 3275

## Resource

What happens when you combine a real customer problem, a no-code prototype, and a team willing to listen to every single call? In this episode of _Just Now Possible_, Teresa Torres talks with Steven Payne (Product Manager), Gabriel Stock (Senior Engineering Manager), and Philipe Steiff (Senior Software Engineer) from Perk—a company that helps businesses eliminate "shadow work" like travel booking and expense management. They share how they built a voice AI agent that calls hotels to verify virtual credit card payments, preventing travelers from arriving to find their rooms unpaid. What started as a hackathon experiment in Make.com became a production system handling over 10,000 calls per week across multiple languages. Along the way, the team learned hard lessons about prompt engineering for voice (numbers, pronunciation, and a very "Karen-like" first version), how to break a single monolithic prompt into structured conversation stages, and why listening to actual calls beats any amount of theorizing. You'll hear how they: - Built a working prototype without writing a single line of backend code - Structured the call into discrete stages (IVR, booking confirmation, payment) to improve reliability - Created two eval systems: one for call success classification, another for conversational behavior - Scaled from five calls a day to tens of thousands per week while maintaining quality This is a detailed look at building AI for real-time human interaction—where the stakes are high and the feedback is immediate.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/just-now-possible-7481489/episodes/from-prototype-to-production-how-perk-built-a-voice-ai-agent-that-makes-10-000-calls-a-week/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/just-now-possible-7481489/from-prototype-to-production-how-perk-built-a-voice-ai-agent-that-makes-10-000-calls-a-week.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.