Presented by
A one-day, invite-only summit providing a first look at the
benchmarks and research that will shape the frontier.
October 8, 2026
San Francisco
Topics
Environment complexity
Evaluating agents in realistic, dynamic, tool-rich environments.
Autonomy Horizon
Measuring how far agents can act independently over long horizons.
Output Complexity
Scoring sophisticated, verifiable, multi-artifact deliverables.
Shaping the frontier of AI