Research
Agent Judge: Solving Long-Horizon Evals for Production Agents
Rishi Gujjar, Andrew Li·May 27, 2026
Blogs
More coming soonCompanyResearch Research Research
Announcing $32M in Funding Led by Lightspeed
May 12, 2026Building the Multi-Agent Infrastructure Behind Judgment Coming soon
Behavior Discovery with RLMs Coming soon
Enabling Self-Improving Agent Harnesses with Evals Coming soon
Subscribe to our newsletter
Get new posts delivered to your inbox.
A Missing Primitive for AI Agent Improvement
Why Behaviors are the missing primitive for AI Agent Improvement.
ProductEnyu Rao·Jul 8, 2026
Agent Judge: Solving Long-Horizon Evals for Production Agents
Why long-horizon agents need agentic judges that can search, verify, and adapt.
ResearchRishi Gujjar, Andrew Li·May 27, 2026
Announcing $32M in Funding Led by Lightspeed
Infrastructure for improving AI agents from production data.
CompanyJudgment Labs Team·May 12, 2026
Climbing the Hills That Matter
Exploring the challenges with current evaluation methods and proposing a new approach grounded in production data.
PerspectiveAndrew Li, Alex Shan·Oct 7, 2025