Play the video in the post belowPost on X
- Views
- 70,298
- Likes
- 181
- Reposts
- 9
Read from X on . Counts change daily.
Yum had collected a personal archive of X posts for content research but was still opening them one at a time to figure out what they had in common. They built a dashboard around Jev that labels each saved post across 8 dimensions, including topic, hook, and writing style, so the whole set is classified rather than read individually.
The dashboard lets them filter by topic and hook, compare engagement across those filters, and jump back to the original posts to see the examples behind a pattern. Labeling the full archive, 1,315 posts, cost about $0.086 in estimated model spend. They describe the result as making their own archive much easier to learn from.
