[ Use case · Sales ]
Can Jev score and route inbound leads?
Yes. Lead scoring is one of Jev's strongest fits: send the lead record, score it for fit, estimate buying intent and route it, all in one request. Public runs report scoring hundreds of leads in seconds for a few cents.
Is it a fit?
Use Jev when
- You get more inbound leads than your team can read, and most are low value.
- Your ideal customer profile fits in a few plain sentences.
- You want a ranked queue for reps, not a fully automated decision on who gets contacted.
Skip it when
- You need a written rationale for each score. Jev returns scores and probabilities, not explanations.
- The score depends on data Jev can't see, such as CRM deal history, and you can't include it in the input.
The questions
One request per lead, 3 questions. Jev answers them in parallel.
- Score
How well does this lead match our ideal customer: B2B companies of 100–2,000 employees with a sales or RevOps team?
Scale: No fit → Weak fit → Plausible fit → Strong fit → Ideal customer
- Noul (yes/no)
Is this person actively looking to buy or implement a solution soon?
Options: Yes · No
- Choice
Who should handle this lead?
Options: Sales · Nurture · Partner · Other
Getting started
[ 1 · Test it in the playground ]
No code needed. Paste a real lead into TypeSafe's playground and ask: “How well does this lead match our ideal customer: B2B companies of 100–2,000 employees with a sales or RevOps team?” with the options No fit, Weak fit, Plausible fit, Strong fit, Ideal customer. 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 lead automatically, call Jev from the system where your leads live. The developer details below include the full request, and the Recipe Pack ships a ready-to-run version.
What people have reported
Lead scoring
self-reported700 leads for 9¢ (13¢ per 1,000), 40 seconds
Romàn, indie software builder · Made with Jev (opens in a new tab)
Self-reported figures are the author's own; we haven't reproduced them. More on the costs page.
Common questions
- How much does lead scoring with Jev cost?
- About 2 cents per 1,000 leads at list price. Scoring 3,000 leads a month costs roughly 6 cents.
- Does Jev replace a CRM lead score?
- It complements it. Jev reads the unstructured text that rule-based scores ignore, such as form messages and job titles. Keep the CRM as the source of truth and write Jev's score into a field.
[ For developers ]Request body, wiring and pitfalls
The request
One request per lead 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": {
"name": "Priya Raman",
"title": "Head of RevOps",
"company": "Northwind Logistics (420 employees)",
"source": "Pricing page form",
"message": "We're replacing our routing rules for ~3k inbound leads/month. Need something live this quarter."
},
"questions": {
"fit": {
"type": "score",
"instructions": "How well does this lead match our ideal customer: B2B companies of 100–2,000 employees with a sales or RevOps team?",
"criteria": [
"No fit",
"Weak fit",
"Plausible fit",
"Strong fit",
"Ideal customer"
]
},
"intent": {
"type": "noul",
"instructions": "Is this person actively looking to buy or implement a solution soon?",
"criteria": {
"true": "Mentions a timeline, budget, active evaluation or a concrete project.",
"false": "Browsing, researching, a student, or a vendor pitching us."
}
},
"route": {
"type": "choice",
"instructions": "Who should handle this lead?",
"criteria": {
"sales": "A potential customer worth a sales conversation",
"nurture": "A potential customer who is early; add to nurture",
"partner": "An agency, reseller or integration partner",
"other": "Job seeker, vendor, spam or not a buyer"
}
}
}
}How to wire it up
- 1.Send each new lead as JSON state with all three questions in one request, so the lead is read once.
- 2.Route to sales when intent ≥ 0.7 and fit ≥ 3; send to nurture below that.
- 3.Send low-confidence route answers (confidence < 0.6) to a human review list.
- 4.Every month, compare 50 Jev decisions with what your team would have done and adjust the wording of the criteria.
Watch out for
- Vague criteria produce vague scores. "Good lead" is not a rubric; "B2B, 100–2,000 employees, has a RevOps team" is.
- Don't send fields you wouldn't want a vendor to see. Strip phone numbers and anything you don't need for the decision.
New to writing Jev questions? Read the question design guide.
Related use cases
Can Jev triage an inbox?
Sort mail into categories, rate urgency and flag what needs a reply.
Can Jev route support tickets to the right team?
Send each ticket to the right queue and flag frustrated customers.
Can Jev moderate user content and catch prompt injection?
Flag spam, abuse and prompt injection before content goes live.