Reliable Agents Need Evals: A Scale AI Workshop

Join Scale AI for Reliable Agents Need Evals, a hands-on workshop on how teams are evaluating AI systems before they reach production, covering how they define "good" for their use case, identify failure modes, and turn evaluation results into meaningful improvements. Only 10% of enterprises have GenAI in production today. We'll break down what separates them from everyone still stuck at POC. The Agenda → 30-minute talk - Scale’s approach to building reliable AI through evals. → 15-minute hands-on walkthrough - We’ll set up an eval for a mock company together, live. → Open Q&A - Bring your questions for two of Scale’s senior eval experts. The Takeaways → Scale’s Eval Field Guide - An early, limited release of the 10-page playbook originally created to train Scale’s Forward Deployed Engineers, now available to enterprise leaders. → Direct access to our eval experts - An opportunity to dig into the questions that matter for your team with Brad and Ryan. → A room of peers - Connect with senior leaders working through many of the same challenges around bringing AI agents into production. Led by → Brad Kenstler — Head of General Agents, Scale AI → Ryan Kappedal — Principal Machine Learning Engineer, Scale AI Stick around afterward for drinks, networking, and time with the Scale team. This event is a part of #LATechWeek—a week of events hosted by VCs and startups to bring together the tech ecosystem. Learn more at www.tech-week.com.

Are you the organiser? Get a private analytics link, and tell us if you are open to sponsors