Abstract
As AI moves from conversation to action, the human role shifts from asking questions to overseeing autonomous agents. But keeping people in the process is only valuable if the interaction is designed to make them effective - not just compliant. In this hands-on workshop, teams will prototype agentic AI experiences grounded in real banking scenarios, designing interfaces where people don't just rubber-stamp AI outputs but genuinely sharpen them. Through interactive exercises, participants will explore patterns that surface the right context at the right moment, structure agent actions for real human judgment, and stress-test their designs against the traps that turn meaningful oversight into approval fatigue and illusory control. You'll leave with practical frameworks for human-agent collaboration where both the AI and the person perform better together.
Topics To Be Covered
Understand the human-in-the-middle pattern and when it matters
Design agent-to-human handoff points that enable real judgment
Identify and avoid oversight anti-patterns like approval fatigue and automation bias
Prototype agentic AI interfaces that amplify human performance
Stress-test human-agent collaboration flows against real-world failure modes
Perfect For
Product Managers and Designers
Developers and Architects
Business and Innovation Leaders
Anyone designing or governing AI-driven workflows
Meet Your Instructor
Jan Zubíček
AI Product Manager, ČSOB
Jan Zubíček serves as AI Product Manager at ČSOB, Czech Republic's leading bankinsurance group and part of KBC Group, where he bridges technical capabilities with business objectives to shape and execute strategic AI initiatives. With over 20 years of experience spanning IT, data, and AI domains, he played a key role in bringing Kate to life - ČSOB's groundbreaking conversational AI assistant that has handled over 10 million customer interactions and set new industry standards for personalized banking services. His current focus is on leading the convergence of business, AI, and IT to bring the next generation of intelligent automation to banking - moving beyond conversational interfaces toward AI that acts on behalf of customers and employees across complex workflows. His expertise combines deep technical knowledge with strategic business insight, gained from working with both startups and enterprise organizations throughout his career.
ADDITIONAL INFORMATION
Time & Place
Tue, March 24
16:15 - 17:45
The Ritz-Carlton Berlin
Salon Tiergarten
Classroom Seating
Max. Capacity: 32 Seats
Secure your seat – registration required.
Notes
Agenda for this session:
Getting Settled - 5 mins
Information Session - 40 mins
Break - 5 min
Individual / Group Exercise - 20 min
Q&A/Discussion - 15 min
Reflection - 5 min
Prerequisits:
Basic understanding of gen AI, agentic AI and LLM
Bring your own laptop
.png)