Using Jev classifiers to mine agent failure modes

Applied Compute @appliedcomputeOriginally posted 2026.09.24

Open original on X

Gap analysis is how our Applied Researchers, like @_brylee10, surface agent failures across billions of tokens of RL traces for our customers. Using our platform, AC2, and low-cost classifiers like Jev, we can catch 85% of failure modes at a fraction of the cost of LLM judges and turn them into training data.

This post quotes another post: “Automated failure mode clustering with Jev in RL training”