The Dialogue Architects

Episode Description

Trust isn’t something you add to voice AI at the end—it has to be designed in from the start.

In this episode of The Dialogue Architects, Lauren Goerz, Staff Product Marketing Manager at Rasa, sits down with Ludwig Sickert to explore how high-trust voice AI systems are built in real enterprise environments. Drawing on his journey from IBM Watson AI to co-founding Logen.AI, Ludwig shares how conversational systems have evolved from simple FAQ bots into deeply integrated, production-grade voice agents.

The conversation examines why trust is especially fragile in voice interfaces and what teams must do to preserve it. Lauren and Ludwig discuss the importance of integrating voice agents with core IT systems, defining a consistent brand voice, and validating AI outputs to ensure reliability at scale. They also break down common implementation challenges—from handling complex business processes to balancing flexibility with governance.

Looking ahead, Ludwig shares his perspective on the future of voice AI, including emerging opportunities around memory and continuity across conversations, and what those capabilities will require from a trust and design standpoint.

This episode is essential listening for product leaders, designers, and engineers building voice AI systems where accuracy, confidence, and user trust are non-negotiable.

[00:00] Introduction and guest welcome
[00:43] Ludwig’s career journey
[02:01] Building high-trust voice agents
[04:01] Challenges and solutions in conversational AI
[07:06] Voice AI implementation strategies
[15:05] Ensuring high-trust AI systems
[18:43] Technical and business considerations
[26:51] The future of voice AI and memory
[30:12] Closing thoughts and farewell

Ludwig Sickert – LinkedIn
Logen.AI
Learn more about trustworthy conversational AI at Rasa: rasa.com

The Dialogue Architects is a podcast from Rasa, hosted by Lauren Goerz, exploring the craft and strategy behind designing conversational AI in the enterprise. Each episode brings together technologists, designers, and product leaders to unpack how dialogue is built, scaled, and governed in real-world systems.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Trust is not a feature—it’s an outcome of good design, clear intent, and disciplined execution.

In this episode of The Dialogue Architects, we sit down with Hans Joachim Belz to explore what it really takes to design conversational AI systems that users—and organizations—can trust.

Drawing on extensive experience across large enterprises including Deutsche Telekom, E.ON, and DHL, Belz shares lessons learned from building and advising conversational systems in complex, regulated environments.

The conversation covers the evolution of conversational design, the role of UX fundamentals in an LLM-driven world, and how teams can balance innovation with risk management. We discuss why disambiguation and clarifying questions remain essential, how trust differs across text and voice interfaces, and what designers should consider when working with multi-agent architectures.

Belz also reflects on what past technology revolutions can teach us about today’s AI moment—offering a grounded, experience-driven perspective for teams building conversational AI that must scale responsibly.

This episode is essential listening for UX designers, product leaders, and AI practitioners focused on creating conversational systems that are reliable, controllable, and human-centered.

[00:00] Introduction to The Dialogue Architects
[00:07] Meet Hans Joachim Belz: From UX Consultant to Conversational AI Engineer
[00:58] Foundations of Conversational Design
[03:21] The Importance of T-Shaped Skills in UX
[04:33] Challenges and Opportunities with Large Language Models
[06:04] Balancing Risk and Innovation in Conversational AI
[12:57] Disambiguation and the Role of Clarifying Questions
[31:00] Voice vs. Text: Designing for Different Modalities
[35:26] The Future of Multi-Agent Architectures
[37:43] Lessons from Past Technological Revolutions
[39:48] Closing Thoughts and Farewell

Hans Joachim Belz – LinkedIn
 

Learn more about trustworthy conversational AI at rasa.com

About The Dialogue Architects

The Dialogue Architects is a podcast from Rasa exploring the craft and strategy behind designing conversational AI enterprises. Each episode brings together technologists, designers, and product leaders to unpack how dialogue is built, scaled, and governed in real-world systems.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

In this episode of The Dialogue Architects, host Lauren Goerz welcomes Alan Nichol, co-founder and CTO of Rasa, to unpack his journey from physics PhD to becoming a pioneer in conversational AI.

Alan reflects on the early chatbot experiments that seeded Rasa’s creation, the lessons learned from the first wave of conversational interfaces, and why today’s AI assistants demand a more thoughtful approach—one grounded in user trust, governance, and real-world problem solving.

Their conversation explores:

• Rasa’s origin story—from side projects to powering global enterprise assistants
• Why early chatbots failed and how modern systems must evolve
• How enterprises can design scalable, maintainable conversational architectures
• The shift from scripted flows to adaptive, AI-driven dialogues
• Why observability, governance, and user-centric design matter more than model size
• How companies can avoid the AI hype cycle and focus on what users actually need
• Actionable advice for teams who want to get started with Rasa

Alan provides guidance for enterprises navigating rapid AI innovation—and a grounded vision of what it takes to build human-machine conversations that truly work. Clarity, responsibility, and building AI that solves real problems.

 

Episode Timestamps: 

(00:00) Introduction to Dialogue Architects
(00:07) Meet Alan Nichol: From Physicist to CTO of Rasa
(00:42) The Origin Story of Rasa
(01:13) Early Challenges and Innovations in Conversational AI
(03:03) Building Bots and the Evolution of NLP
(07:40) The Rise of Rasa and Open Source Contributions
(12:36) Company Culture and Hiring Philosophy at Rasa
(15:42) Maintaining Integrity and Trust in AI Development
(19:18) Early Bets and the Evolution of NLP Classifiers
(20:02) Challenges with Classification Paradigms
(24:14) The Shift to LLMs and Honest AI
(25:20) The Overuse of Conversational Interfaces
(28:06) AI Assisted Coding and Abstractions
(31:19) The Future of Conversational AI
(37:58) Advice for Enterprises and Final Thoughts

Links & Resources:

• Rasa Official Site
• Alan Nichol on LinkedIn
• Lauren Goerz on LinkedIn

Subscribe & Follow The Dialogue Architects on YouTube, LinkedIn, and Apple Podcasts

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

In a world powered by AI and automation, conversational AI is now a critical business function. On The Dialogue Architects, host Lauren Goerz brings together industry leaders and practitioners to explore how to design scalable, trustworthy conversations that enterprises can rely on—today and into the future. Presented by Rasa.

Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.