JevMade hello@JevMade.com
← Back to guides

JevMade field notes / Research writeup

Testing an AI choice tool inside a workout coaching app

A workout app tested an AI tool named Jev to manage coaching messages. This report shows where the tool succeeded in checking answers and where it lost to the app's existing software.

Original by RIRLiftEvaluation

Listen to this guide

JevMade’s plain-English explanation

0:00 /

AI narration

Credits

“Lifting App Tests Jev Decision Model for Workout Coaching” by RIRLift. Read the original source.

This expanded guide is an AI-narrated adaptation prepared by JevMade. It expands the source’s essential ideas, examples and caveats in JevMade’s own words and is not a word-for-word reading. The synthetic voice does not imitate the author or imply their endorsement.

Our summary

The creators of a workout app tested Jev, an AI tool that chooses from options instead of writing answers. They wanted to check coaching messages and replies, then find out whether Jev could replace software already running on a user's phone.

The team checked whether messages concerned exercise, needed more thought, or contained instructions trying to mislead the assistant. They also checked drafted replies against workout records. Separately, they compared Jev with their existing software for identifying muscle groups from a person's workout request.

Jev did well in the reported message and reply checks, but lost the muscle-group comparison overall. The app kept its existing phone-based tool. These results describe one team's tests, with different examples and languages for each task; they do not establish that Jev works equally well everywhere.

Key takeaways

  1. The app tested specific choices rather than asking Jev to write coaching advice.
  2. Message-topic checks covered twenty languages; the other checks used different test sets.
  3. The existing phone-based tool beat Jev overall at identifying requested muscle groups.

The test results and costs were reported by the app's creators and were not independently verified. They describe what happened in this specific app rather than proving how the tool works everywhere.

Article · Source reviewed · Original published

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