Jev for sales teams: what it can do and what it costs

Jev, TypeSafe AI's decision model, answers a question about text with a value your software can use: one option from a list, a score, or a yes/no probability. That suits the small, repeated decisions in the middle of this work.

These are the jobs on this site that fit sales teams best. Each has its own page with the questions to ask, the pitfalls and a worked example.

• Rank inbound leads by fit and intent before a human looks at them. 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.
• Sort mail into categories, rate urgency and flag what needs a reply. Email triage is the most widely reproduced Jev workload: one request per email can assign a category, rate urgency and flag whether a human needs to see it.
• Surface only the papers and headlines that match what you care about. Relevance filtering is a natural Score question: describe what you care about, and Jev rates each abstract or headline against it.

• Jev for lead scoring
• Jev for email triage
• Jev for research and news filtering

Jev lists $0.042 per million input tokens with output free, so the cost depends on how much text you send and how many questions you ask about it. At the typical volumes the use-case pages assume, the calculator estimates:

• Leads (lead scoring): about 1.9¢ per 1,000, at 3 questions and about 250 tokens each.
• Emails (email triage): about 2.4¢ per 1,000, at 3 questions and about 400 tokens each.
• Papers (research and news filtering): about 2.1¢ per 1,000, at 3 questions and about 350 tokens each.

• Cost calculator
• Jev pricing and real runs

A plain way to begin, in order:

• Describe a good lead in words, the way you would brief a new colleague, and turn it into a Score question.
• Add a yes/no question for buying intent and a Choice for which rep or team gets the lead.
• Run last quarter's leads through it and check whether the high scores are the ones that actually closed.
• Use the score to order the queue first, and only automate routing once the ordering looks right.

• How to use Jev

A score is only as good as the description of a good lead you give it. If your closed-won history disagrees with the score, change the description, not the model.

From the use-case pages, Jev is not the right choice when:

• You need a written rationale for each score. Jev returns scores and probabilities, not explanations.
• You want replies drafted. Jev can't generate text; pair it with a language model for the emails that need one.
• You need summaries of what you keep. That's a language model's job.

• What Jev can't do

Sales is where a cheap, fast ranking pays off most, because speed to reply matters. Treat the score as a way to read the queue in a better order, not as a verdict, and keep a human on the first conversation.

The figures above are list-price estimates, not measured bills, and the accuracy claims on the linked pages are the published runs' own. Test Jev on a labelled sample of your own data before you rely on it.

• What is a decision model?