CONTENT / HOSE
WRITE · CHALLENGE · REFINE
THE DRAFT EVOLUTION LAB

Good drafts.
Better challengers.

A writer makes the next move. Jev judges the work. Keep what improves, see what gets rejected, and stop before it turns into slop.

View latest run ↓
WRITER × JUDGE
GPT-4.1 mini / Jev
Drafts only. Nothing posts to X.
01 / WRITEStarting draft
02 / MUTATENew challenger
03 / JUDGEFixed rubric
04 / KEEPBetter or stay
NO MANUFACTURED RESULTS

Your next post starts here.

Choose a topic and a number of rounds. Every score and revision shown here comes from an actual model call.

What actually makes a challenger win?
  1. GPT-4.1 mini creates a draft or rewrites the current best, targeting its weaker dimensions.
  2. Jev independently rates hook, clarity, audience fit, usefulness, shareability, voice and conversation potential against the same fixed descriptive rubric. Weights are fixed for the chosen goal: shares or replies.
  3. Code enforces format limits. Jev flags unsupported specific claims and engagement bait. These checks can miss things: review before posting.
  4. A challenger must be eligible and gain more than one rubric point. A separate blind A/B judgment, with random presentation order and no scores, must also prefer it. Ties keep the incumbent.
  5. Stop at the round limit or after three non-improving rounds. A higher score is not evidence of higher real-world engagement.