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

Guests

• Steven Payne, Product Manager, Perk
• Gabriel Stock, Senior Engineering Manager, Perk
• Philipe Steiff, Senior Software Engineer, Perk

What we cover in this episode

• How Perk's team identified an AI use case by connecting prior experimentation with a real operational problem
• Why they chose Make.com for prototyping—and shipped to production without touching backend code
• The evolution from a single prompt to structured conversation stages (IVR handling, booking confirmation, payment request)
• How breaking up the agent's task dramatically improved reliability
• Building two eval systems: classification for success rates and LLM-as-judge for conversational behavior
• Why the team still listens to calls manually even with automated metrics
• The challenge of prompt engineering for voice: numbers, booking references, and text-to-speech markup
• Lessons learned from expanding to German (prompts in native language improve results)
• How this project uncovered other operational problems they didn't know existed

Resources & Links

• Perk
• Make.com – No-code automation platform used for the prototype
• Twilio – Voice/telephony provider
• 11 Labs – Text-to-speech provider (used in early experiments)

Chapters

00:00 Introduction to the Team 01:54 Understanding PERK's Mission 02:59 Challenges in Travel Booking 07:27 AI Solutions for Customer Care 09:52 Prototyping with AI and Voice 17:00 Implementing AI in Production 25:51 Learning Through Trial and Error 26:40 Prompting Challenges and Solutions 27:58 Iterating on Prompts and Evaluations 30:08 Scaling and Production Challenges 32:43 Advanced Evaluation Techniques 35:32 Real-World Applications and Success 49:07 Future Directions and Expansion 53:53 Conclusion and Team Reflections