Evally
Start free
Content & growth

Ad brief scorer

Score an ad brief on its hook, brand fit and survival odds before anything gets shot.

Write a brief off a proven pattern, then score it like a creative director would: how hard the hook stops a scroll, whether it sounds like your brand, whether every claim holds up against your product facts, and how likely it is to keep running past 60 days. Only the strongest get shot.

Use this judgeCustomize it

Try it live

Real calls to Jev. Pick an example or paste your own.

Examples
174
124
142
107
No verdict yet

Pick an example or paste your own input, then run it.

Under the hood

Every question and rule, in the open. Fork it to change any of them.

What it asks

Reads brief, brand, facts and pattern, then asks 5 questions in one call.

  1. Q1HookScore

    How hard does the opening line of the brief stop someone scrolling?

    1. 0Flat
    2. 1Okay
    3. 2Strong
    4. 3Scroll-stopping
  2. Q2Brand fitScore

    How well does the brief fit the brand described in brand: its voice, its audience and its limits? Without brand notes, judge whether it sounds like a credible brand.

    1. 0Off brand
    2. 1Partly
    3. 2Good fit
    4. 3Unmistakably them
  3. Q3Claims hold upYes / no quotes evidence

    Are the brief's claims about the product supported by the facts? A personal story or the price of an alternative isn't a product claim. Without facts, are the product claims believable and free of promises an ad reviewer would reject?

  4. Q4Follows the patternYes / no

    Does the brief follow the pattern: the same format, and an opening that gets to the point as fast as the winning ads? Without a pattern, does it open on its single strongest idea?

  5. Q5SurvivalScore

    How likely is an ad made from the brief to keep running for 60 days or more, judging by how specific, believable and repeatable it is?

    1. 0Burns out fast
    2. 1A few weeks
    3. 2Could last
    4. 3Built to last

How it decides

Rules run in code, top to bottom. The first one that matches gives the verdict.

  1. 1
    If Claims hold up < 0.5Cut it
  2. 2
    If Brief score ≥ 72Shoot it
  3. 3
    If Brief score ≥ 45Revise
  4. ·
    DefaultCut it
Brief score

A 0-100 score weighted from Hook ×3, Brand fit ×2, Claims hold up ×2, Follows the pattern ×1.5, Survival ×2.5.

Call it from your code

Every template runs as-is with an API key, no setup: POST /api/v1/judges/ad-brief-scorer/run.

curl -X POST https://tryevally.com/api/v1/judges/ad-brief-scorer/run \  -H "Authorization: Bearer $EVALLY_API_KEY" \  -H "Content-Type: application/json" \  -d '{  "input": {    "brief": "Talking head demo. Opens: \"I'\''m a colorist, and this is the 20-minute routine I'\''d do on my own mom.\" She mixes, applies and waits on camera, then shows the result in daylight.",    "brand": "Warm, plain-spoken, a little funny. For women 40+ who color at home. Never shame gray hair; never promise permanent results.",    "facts": "Permanent ammonia-free color. 17 shades. $12.98 per kit. Covers 100% of grays in clinical testing. Lasts up to 8 weeks. Results in 20 minutes.",    "pattern": "Talking head demo. Survivors open on a cost or a time the viewer recognises, then show the product working."  }}'

Seen in the wild

Community builds on Jev that use this pattern. Not affiliated with Evally.

  • Jev for Meta Ads
  • Ad creative teardown

More in Content & growth