JevMade

Sign in
← Back to guides

JevMade field notes / Practitioner tip on splitting questions

Split one big Jev question into small checks your code combines

Nathan Flurry of Rivet shares a short X post on moving a support-severity check from one broad Jev question to several small yes/no questions combined in ordinary code.

Original by Nathan FlurryClassification

Listen to this guide

JevMade’s plain-English explanation

Expanded guide unavailable: the complete source text could not be retrieved.

0:00 /

Our summary

This is a short post on X from Nathan Flurry, founder of Rivet, published on 18 November 2026. He says his team first asked Jev one broad question: give the severity of an issue, with a list of what each level means. He reports that this gave mediocre results, and that it treated Jev like a model that reasons its way to a conclusion.

After reading the docs, the team split the job into tiny questions: did the service go down, is the customer blocked with no workaround, is something broken. Ordinary code then picks the severity from the answers. He says this works well, and that when a ticket is weighted badly they have a language model add it to a test suite, adjust the logic and re-check old issues.

It is one team's account in a social post, with a screenshot JevMade could not read and no shared code, so the results cannot be checked. The post lists how many Jev questions their internal support classifiers ask, for example 13 for support classification and 6 for severity. Treat those counts as one example, not a target.

Key takeaways

  1. Ask Jev small, specific questions and let your own code reach the conclusion, because Jev is not built to reason to one.
  2. Turn a badly weighted ticket into a test case, adjust the decision logic and re-check old tickets to improve it.
  3. Expect to ask many questions per classifier; Rivet reports 13 for support classification and 6 for severity.

This is one team's account in an X post, not a tested benchmark. JevMade did not reproduce it, could not read the screenshot of the real classifier, and saw no shared code. A TypeSafe account (Allie) quote-posted it and called it a good example of System One thinking: decompose your problems.

X (Nathan Flurry) · Original published

Read the original guide Opens the author’s site in a new tab.

Your note

Only you can see this. Clear the text and save to remove it.

Keep what you save

Sign in to keep bookmarks and private notes on every device. We email you a link; there is no password, and the same link creates your account.