top of page

Voice Agent IRL: On-Guard, Real-Time, and Ready to Talk

Abstract

Go behind the scenes with the ABN AMRO team as they share the journey of building a production-ready GenAI Voice Agent designed for natural, human-like customer conversations. Discover how the GPT Realtime API enables low-latency, speech-to-speech interactions while maintaining flexibility and conversational quality. Learn how the team designed, tested, and refined guardrails to ensure safe and reliable voice experiences without compromising usability. The session will also explore how the Voice Agent is monitored in real time, evaluated offline, and continuously improved based on performance insights and real-world learnings.

Topics To Be Covered

  • Build production-ready GenAI voice agents

  • Design effective real-time AI guardrails

  • Reduce latency without sacrificing quality

  • Monitor and evaluate voice agent performance

  • Lessons from deploying enterprise voice AI

Perfect For

  • AI Engineers

  • Conversational AI Teams

  • Solution Architects

  • Product Managers

  • Enterprise AI Leaders

Meet Your Speakers

Michael Mo

AI Engineer, ABN AMRO

Michael is a System Architect and AI Engineer at ABN AMRO, where he works on designing and developing solutions for conversational AI applications. With his academic background in Artificial Intelligence, Mathematics and Computer Science, Michael applies his expertise to develop innovative yet robust systems and tooling that support customer digital experiences in the banking sector. He is particularly passionate about building user-friendly solutions that provide value to both customers and employees, ensuring that technology bridges the gap between functionality and ease of use.

Gönül Aycı, PhD

AI Engineer, ABN AMRO

Gönül Aycı, PhD, is an AI Engineer at ABN AMRO, where she develops conversational AI and voice bot solutions that help customers through intelligent, user-centric experiences. She holds a PhD in Computer Engineering with a specialization in Trustworthy AI, focusing on building intelligent systems that are transparent, reliable, and capable of acting responsibly on behalf of users. Before joining the Conversational AI team, Gönül worked as a Data Scientist, designing and deploying machine learning solutions for business-critical applications. She is also an active advocate for AI education and women in technology, regularly sharing practical insights on machine learning and generative AI through her writing, speaking, and community involvement.

ADDITIONAL INFORMATION

Time & Place

Thu, Nov 26

14:00 - 14:30

Matterhorn III

Limited to 40 participants.

Secure your seat – registration required.

Notes

Agenda for this session

  • 20 min presentation + Audience Q&A

REGISTRATION

In order to register to this session you must hold a Pro or Max Pass.

Limited Seating Still Guaranteed

WhatsApp button (66 x 66 px).png
bottom of page