JevMade hello@JevMade.com
← Back to guides

JevMade field notes / Evaluation walkthrough

Using TypeSafe's Jev for evals

Annabell Schäfer builds a Jev evaluator for user disagreement, showing how to pair replies with later reactions and save the verdict and probability in Langfuse.

Original by Annabell SchäferEvaluationLangfuse blogOriginal published Source reviewed

Before you dive in

What you’ll find in the original

  1. Collapse consecutive generations with the same user message into one turn, then judge its final reply against the next distinct user message. Otherwise an internal tool step can be mistaken for a user reaction.
  2. A Noul returns the probability of true, without a separate confidence field. Keep that probability alongside the verdict, pin the model, and choose a threshold using examples from your own application.
  3. Page through observations, sort them chronologically, and use stable score identifiers and timestamps so reruns update the same score. Flush buffered events before the script exits.
Worth knowing

The example detects the user's expressed disagreement, not whether the assistant was objectively wrong. Its 0.7 threshold is an example policy, not a validated default. The code was source-reviewed, not run against a Langfuse account.