[ Use case · Marketing ]
Can Jev classify ad copy and creative angles?
Yes, for text. Jev can tag each ad by angle, rate hook strength and check it against your policy list in a single request, which makes it practical to label thousands of competitor or historical ads.
Is it a fit?
Use Jev when
- You're analysing a large library of your own or competitors' ads.
- You want consistent tags so you can compare angles against performance.
Skip it when
- The creative is image- or video-only with little text.
- You want new ad copy generated.
The questions
One request per ad, 3 questions. Jev answers them in parallel.
- Choice
What is the main persuasion angle?
Options: Pain · Outcome · Proof · Offer · Curiosity
- Score
How strong is the first line as a scroll-stopping hook?
Scale: Weak → Average → Strong → Exceptional
- Noul (yes/no)
Does the ad make a specific claim that could need substantiation (numbers, guarantees, health or income claims)?
Options: Yes · No
Getting started
[ 1 · Test it in the playground ]
No code needed. Paste a real ad into TypeSafe's playground and ask: “What is the main persuasion angle?” with the options Pain, Outcome, Proof, Offer, Curiosity. You'll see the answer and its probability.
Open the playground (opens in a new tab)[ 2 · Use an existing tool ]
We haven't found a ready-made tool for this workload yet. These directories track what's been built on Jev:
Made with Jev (opens in a new tab)Jev.Store (opens in a new tab)JevHunt (opens in a new tab)
[ 3 · Integrate it ]
To run it on every ad automatically, call Jev from the system where your ads live. The developer details below include the full request, and the Recipe Pack ships a ready-to-run version.
Common questions
- Can Jev tell me which ad will perform best?
- Not directly. It gives consistent labels and scores; join them to your real performance data to learn which angles work for you.
[ For developers ]Request body, wiring and pitfalls
The request
One request per ad with all 3 questions batched over the same state, so Jev reads the state once. Keys below are the names you'll see in the response.
{
"model": "jev-latest",
"state": "Platform: Meta — Headline: \"Stop losing leads at 2am\" — Primary text: \"Your form fills don't sleep. Route every inbound lead in under a second and wake up to a sorted pipeline. Free 14-day trial.\"",
"questions": {
"angle": {
"type": "choice",
"instructions": "What is the main persuasion angle?",
"criteria": {
"pain": "Leads with a problem or fear",
"outcome": "Leads with a result or benefit",
"proof": "Leads with testimonials, numbers or logos",
"offer": "Leads with a discount, trial or deal",
"curiosity": "Leads with a question or tease"
}
},
"hook": {
"type": "score",
"instructions": "How strong is the first line as a scroll-stopping hook?",
"criteria": [
"Weak",
"Average",
"Strong",
"Exceptional"
]
},
"claims_risk": {
"type": "noul",
"instructions": "Does the ad make a specific claim that could need substantiation (numbers, guarantees, health or income claims)?"
}
}
}How to wire it up
- 1.Collect ads (yours from the ad manager, competitors' from public ad libraries) into a sheet.
- 2.Run the three questions per ad and join the results to spend and CTR.
- 3.Look for angles that are overused by competitors and underused by you.
Watch out for
- Hook strength is subjective. Calibrate the rubric on 20 ads your team has already judged.
New to writing Jev questions? Read the question design guide.
Related use cases
Can Jev power semantic search?
Re-rank search results by how well each one matches the query.
Can Jev make decisions inside an AI agent?
Pick the next action in an agent loop in milliseconds.
Can Jev score and route inbound leads?
Rank inbound leads by fit and intent before a human looks at them.