[ Use case · SEO ]
Can Jev classify keywords by search intent?
Yes. Search intent is a textbook Choice question with four well-known classes: informational, commercial, transactional and navigational. Run a keyword export through Jev and get intent plus a relevance score per keyword, for under a cent per 1,000.
Is it a fit?
Use Jev when
- You work with keyword exports of thousands of rows.
- You want to cluster keywords by intent before writing anything.
Skip it when
- You need search volume or difficulty. That data comes from SEO tools, not a model.
The questions
One request per keyword, 2 questions. Jev answers them in parallel.
- Choice
What is the searcher's main intent?
Options: Informational · Commercial · Transactional · Navigational
- Score
How relevant is this keyword to the site described?
Scale: Off-topic → Loosely related → Relevant → Core topic
Getting started
[ 1 · Test it in the playground ]
No code needed. Paste a real keyword into TypeSafe's playground and ask: “What is the searcher's main intent?” with the options Informational, Commercial, Transactional, Navigational. 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 keyword automatically, call Jev from the system where your keywords live. The developer details below include the full request, and the Recipe Pack ships a ready-to-run version.
Common questions
- How much does it cost to classify 10,000 keywords with Jev?
- About 7 cents at list price.
[ For developers ]Request body, wiring and pitfalls
The request
One request per keyword with all 2 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": {
"keyword": "jev api pricing per million tokens",
"site": "A resource site for developers building with Jev"
},
"questions": {
"intent": {
"type": "choice",
"instructions": "What is the searcher's main intent?",
"criteria": {
"informational": "Wants to learn or understand something",
"commercial": "Comparing options before a purchase",
"transactional": "Ready to buy, sign up or download",
"navigational": "Looking for a specific site or page"
}
},
"relevance": {
"type": "score",
"instructions": "How relevant is this keyword to the site described?",
"criteria": [
"Off-topic",
"Loosely related",
"Relevant",
"Core topic"
]
}
}
}How to wire it up
- 1.Export keywords from your SEO tool as CSV.
- 2.Send each keyword with a one-line site description as state.
- 3.Drop keywords with relevance < 1.5, then group the rest by intent to plan pages.
Watch out for
- Mixed-intent keywords are common. Use the probabilities, not just the top choice — a 58/34 split tells you the page should serve both.
New to writing Jev questions? Read the question design guide.
Related use cases
Can Jev classify ad copy and creative angles?
Tag ads by angle and hook strength, and pre-check them against policy.
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.