ML6 x Women in AI: Agents You Can Trust

Building an AI agent has never been faster. But how do you build one that people can actually trust? And as a user, how do you know when to rely on it? Join Women in AI Berlin and ML6 for an evening on building reliable, testable AI agents. Women working in AI engineering will share practical experience and lessons learned in a series of short talks. You don’t need to have built an agent before to join. Program 18:00 - Walk-in & Welcome 18:30 - Introduction by Women in AI & ML6 18:40 - Building Trust on Shifting Ground by Cato van Willige 19:05 - Who gets to say no to an AI agent? Building approval gates outside the model by Emma Pulbrook 19:30 - How do we define and evaluate successful work by an AI agent? By Gráinne McKnight & Bozhidara Ognyanova 19:55 - The EU AI Act Doesn't Trust Your LLM And Your Architecture Shouldn't Either by Fatime Zekjiri 20:20 - Wrap-up & Networking 21:00 - See you soon! We'll provide food and drinks, including vegetarian and vegan options. We look forward to seeing you there!