DS Talks: Building AI Agents That Actually Work

When? Tuesday, 24 November 2026, 18:00–19:00.

Where? Faculty of Computer and Information Science, Večna pot 113, Ljubljana. Lecture room 22.

What?

Building useful AI agents takes much more than a capable language model: they also need to be reliable, safe, and scalable. Larsen Cundrič, a Slovenian engineer who studied computer science in Ljubljana and now works in Silicon Valley, shares lessons from building AI agents and products at a fast-moving startup:

• How AI agents work: the basics of agents that interact with browsers, tools, and external systems.
• Engineering challenges: reliability, sandboxing, infrastructure, and scaling.
• Building AI products: engineering and development practices in a field that changes every few months.
• From Ljubljana to Silicon Valley: his career path, opportunities in the US, and advice for people entering the field.

The talk focuses on general engineering principles, public technologies, and personal experience rather than company-specific implementations. It’s aimed at students, engineers curious about AI agents, and anyone considering a career in the US tech scene. The talk is followed by an open Q&A and refreshments.

Want to attend? Register here.