Building AI Agents That Actually Work

How do you build an AI agent that doesn’t fail? Learn from the successes and failures of industry practitioners and start building advanced AI agents that can handle business workflows and operate safely in production environments.

Jun 24, 2025

18:00 CET | 09:00 PST

Building AI Agents That Actually Work

How do you build an AI agent that doesn’t fail? Learn from the successes and failures of industry practitioners and start building advanced AI agents that can handle business workflows and operate safely in production environments.

Jun 24, 2025

18:00 CET | 09:00 PST

Building AI Agents That Actually Work

How do you build an AI agent that doesn’t fail? Learn from the successes and failures of industry practitioners and start building advanced AI agents that can handle business workflows and operate safely in production environments.

Jun 24, 2025

18:00 CET | 09:00 PST

Building AI Agents That Actually Work

How do you build an AI agent that doesn’t fail? Learn from the successes and failures of industry practitioners and start building advanced AI agents that can handle business workflows and operate safely in production environments.

Jun 24, 2025

18:00 CET | 09:00 PST

Building AI Agents That Actually Work

Where:

Online

Date:

Jun 24, 2025

18:00 CET | 09:00 PST

Overview

This webinar will focus on the practical challenges of building reliable, safe AI agents for real-world applications. Our speakers will share their experiences overcoming the technical hurdles of implementing and testing robust agentic systems in enterprise workflows.

We’ll answer the questions everyone’s asking:

  • How do you build an AI agent that doesn’t fail? Navigate common pitfalls and pain points in agent development, with lessons on overcoming limitations from the perspective of Helio AI.

  • How can agents automate operations? Transform existing business processes into sophisticated agentic workflows for efficient automations.

  • What about safety and security? Test agent safety and detect vulnerabilities in interactive environments, with real examples from red teaming a computer use AI agent.

AI practitioners, technical leads, and business leaders planning strategic AI implementation will benefit from real-world engineering insights and security considerations for developing production-ready AI agents.

Participants

Natia Kukhilava

CTO, Helio.AI

Profile link

Shirsha Ray Chaudhuri

Director of Engineering, TR Labs at Thomson Reuters

Profile link

Boris Obmoroshev

R&D Analytics Director, Toloka

Profile link

Ekaterina Artemova

ML Researcher, Toloka

Profile link

Registration

Don't miss a thing!

Get all the latest on our webinars, meetups, and other events.

Don't miss a thing!

Get all the latest on our webinars, meetups, and other events.

Don't miss a thing!

Get all the latest on our webinars, meetups, and other events.