HumanX 2026
Sponsor
VIEW ALL SPONSORS
Scale AI
At Scale, our mission is to develop reliable AI systems for the world’s most important decisions. Our products provide the high-quality data and full-stack technologies that power the world’s leading models, and help enterprises and governments build, deploy, and oversee AI applications that deliver real impact.
Previous Sessions
HumanX 2026 San Francisco
To Build Reliable AI, Start with Evaluations: How to Ship Enterprise AI
Most AI projects stall because leaders can’t confidently answer whether a model is safe and reliable enough to ship. The longer that question goes unresolved, the wider the technology gap grows in your organization as the frontier of AI progresses.
In this masterclass, we’ll introduce a practical Evaluation-Driven Development framework, informed by our work deploying AI at large-scale enterprises like Mayo Clinic, Pfizer, and T-Mobile. You’ll learn how to define clear quality standards, measure performance in a structured way, and reduce risk before launch.
You’ll leave with a straightforward approach to building custom rubrics, aligning stakeholders, and moving from experimentation to production with confidence.
In this masterclass, we’ll introduce a practical Evaluation-Driven Development framework, informed by our work deploying AI at large-scale enterprises like Mayo Clinic, Pfizer, and T-Mobile. You’ll learn how to define clear quality standards, measure performance in a structured way, and reduce risk before launch.
You’ll leave with a straightforward approach to building custom rubrics, aligning stakeholders, and moving from experimentation to production with confidence.
Best for:
Technology
Sponsored by Scale AI
Presented by
Mihir Pandya
Director, Engineering
Scale AI
AGENDA AT A GLANCE
READY TO BE PART OF IT?
Don't miss out on the premier AI event of the year! Get your tickets now and be part of the future of technology!