JEV scores your video before you film it
hey
JEV is insane. it scores your video before you film it, so you know if it's worth making.
let me explain.
most AI tools write. ChatGPT and Claude generate scripts, hooks, titles, whatever you ask for.
JEV is different. it's a new model from TypeSafe AI, and it doesn't write anything. it judges.
you give it information plus specific questions. it returns decisions, scores, and confidence your software can use right away.
LLMs write. JEV decides.
why this matters
AI made content cheap. anyone can generate 20 hooks in a minute.
so the bottleneck moved. it's no longer "can i make this?" it's "which idea deserves 6 hours of production?"
most of us answer that with instinct. sometimes it works. sometimes it burns a whole day.
JEV adds a scoring layer between the idea and the filming.
how i use it for Shorts
i pulled 248 Shorts from the AI niche. JEV scored each caption for hook strength, structure, format, and niche fit. then i put the scores next to real views.
now i paste a draft script and see if it beats my baseline before i film.
the biggest insight: format mismatch matters more than the raw score. a strong hook in a rant format can still lose in a niche where tutorials win.
how i use it for YouTube
long-form has a different decision point. title and thumbnail decide the click.
i scored 415 titles from big AI channels. for a new video, i enter the draft title, length, and thumbnail concept. i can test 5 title variations in 90 seconds instead of publishing one and hoping.
can it predict virality?
no. and i don't trust anyone who says a tool can.
virality depends on trust, timing, delivery, editing, and a dozen things text can't capture.
but it catches weak hooks and format mismatches before they cost you a day. that's enough.
the loop
research. score. improve. publish. learn.
one number before filming decides if you spend 6 hours or 6 minutes.
i walk through the full dashboard in the video:
→ what JEV is
→ why it matters
→ how to score Shorts before filming
→ how to test YouTube titles and thumbnails
i'm building this workflow into AI Topia for both Shorts and YouTube. if you want this running for your content:
hit reply and tell me: would you score your videos before filming? what would you test first?
Joon
Joon Ahn's newsletter
marketers spend most of their week making small decisions, not writing. which lead is worth contacting. which message fits that lead. which ad creative to test. is this search term coming from a buyer. is this ad fatiguing. does the landing page match the promise. each one is small. thousands per week makes them expensive. last week i wrote about JEV, the decision model from TypeSafe AI. quick recap: an LLM generates an answer word by word. JEV takes a situation and a fixed list of possible...
hey. new long-form video is up. this one solves the most annoying problem in ai video: your character looks different in every shot. the short version: stop generating videos from one random portrait. build two reference files first. one defines who the character is. one defines how the shot looks. then every scene you generate inherits both. i just published the full build: How to Make Consistent AI Characters with GPT Image 2.5 + Seedance. same character across three separate videos....
hey. new long-form video is up. i think short-form editing just changed and most people haven't noticed yet. the short version: you describe the edit in plain english. astra analyzes the footage, marks where to cut, and builds the motion graphics inside ae. i never open the timeline. i just published the 12-minute full build: GPT-6 Astra Changes Short-Form Editing Forever. same avatar video on the left, the astra + after effects edit on the right. same script, same voice, same avatar. only...