Featured · Research
From Agent Evaluation to Episode Learning
How long-running enterprise episodes can provide evidence to discover better policies—and demonstrate that they work.
4 min readRead article
The Spyne blog
Ideas for agents that improve.
From the first task to the next breakthrough.
Perspectives on enterprise context, learning from execution and building models that work where you do.
02 · Research
From Generative Judges to Decision Models: Does Jev Change the Game for Agentic Measurement and Learning?
Can better measurement of an episode lead to better learning from it?
4 min readRead article