Make agents measurable
Reliable Agents Need Evals: A Scale AI Workshop
· Arts District
Scale AI runs a workshop on defining evaluation criteria, identifying failure modes and improving agent reliability.
An independent pick by Superpower Daily

Why this made our list
A named technical team and a live evaluation walkthrough make this one of the most practical choices for teams moving agents into production.
Who it’s for
Builders · Operators
People on the program
- Brad Kenstler (Scale AI)
- Ryan Kappedal (Scale AI)
Before you go
Includes a talk, hands-on walkthrough and open Q&A.
Saving this event does not reserve a place. Complete registration on the organizer’s page.
Superpower Daily
Get the daily briefing Keep the good ideas coming.
AI news, the people building it, and what happens next. In your inbox.
Independent guide by Superpower Daily. Event information and city photography: Tech Week. No affiliation or endorsement implied. Guide data.


