Opens in a new tab

About speaker

Bálint Horváth

LOGINET

Head of Product & Innovation

Bálint is Head of Product & Innovation at LogiNet and co-founder of StickyPrompts. He works primarily on the company’s own SaaS and AI products, manages AI projects, and oversees client solutions technically. He also drives the adoption of AI and new tools across the company, and educates both the internal team and other companies on how to use AI in practice.

He has been coding since age nine and started out as a developer, and that technical foundation has stayed with him through every role since. He has spent more than a decade in eCommerce and has seen software from every side: as a developer, SEO and marketing consultant, IT leader, entrepreneur, head of product at a SaaS startup and solution architect. He has built systems, led teams, run his own business and sold both digital and physical products, including, at one point, baby products. This gives him a practical, end-to-end view of software, from the first line of code to the customer.

His focus is on how software gets created, how to maximize the value it delivers, and how to turn applications into marketable products.

Outside work he does improv, mentors students and startups, trains, and researches hard tech. Despite his job, you won’t find him running AI agents in the background just to keep them busy.

Talk details

October 1

14:00 – 15:00
thu 1
14:00 – 15:00
Workshop
Central Workshop Area

Build the Harness: A Hands-On Challenge in AI Agent Reliability

Bálint Horváth
Bálint Horváth Head of Product & Innovation at LOGINET
AI Agent

A prompt and a model alone don’t make an agent you can rely on in a company. What makes it accurate, secure and trustworthy is the harness around it, and getting that right takes more decisions than most teams expect.

In this hands-on challenge, you compete solo or as a team. You get a set of example tasks from a corporate setting and build an agent to solve them, running on real AI models with a token budget. Every attempt gets scored, and the highest score wins.

Then we look behind the scoreboard: how the agents performed on inputs they had never seen, which approaches held up, which ones broke, and what a genuinely strong solution looks like.

You leave with a practical understanding of what it takes to build AI agents that work reliably in a real company.

No coding and no preparation needed, AI tokens are provided. Bring a laptop, at least one per team.

See more details →

Data

Leadership

Product

AI/ML

UX/UI

Join the event!

Stand on the shoulders of giants and build alongside the people shaping what comes next.

Save the Date

Add the 2026 conference to your calendar