Decide first.
Generate second.
Jev is a decision model. It never writes text. You send a situation and typed questions, and it returns one calibrated probability per question in about 100 ms, for $0.042 per million tokens. Put it in front of anything expensive.
Fit and priority from a CRM record, with the whole distribution returned.
Free starter credits cover thousands of decisions. Or copy the code below and run it with your own key.
Answers arrive here as probabilities, one card per question, in about 100 ms. No text to parse, nothing invented outside the options you gave.
A CRM webhook calls this on every new lead; no model writes anything.
What to do with the numbers
- hot_lead > 0.7 and fit ≥ 2 → tier1 regardless of the tier answer.
- Report conversion per tier weekly; move the thresholds, not the questions.
This exact request, in code
curl https://api.companyfabric.com/v1/decisions \
-H "Authorization: Bearer $COMPANYFABRIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "typesafe/jev-latest",
"state": {
"company_size": 120,
"industry": "SaaS",
"region": "EU",
"source": "webinar",
"pages_viewed": 14,
"demo_requested": true,
"budget_mentioned": "yes",
"timeline": "this quarter"
},
"questions": {
"hot_lead": {
"type": "noul",
"instructions": "Is this lead worth a personal reply within 24 hours?"
},
"fit": {
"type": "score",
"instructions": "How well does this company fit an API product for developers?",
"criteria": [
"Poor fit",
"Possible",
"Good fit",
"Ideal customer"
]
},
"tier": {
"type": "choice",
"instructions": "Which queue?",
"criteria": {
"tier1": "Founder or AE reaches out today",
"tier2": "SDR sequence this week",
"nurture": "Automated emails only"
}
}
}
}'Needs a CompanyFabric key, or add your own TypeSafe key in the BYOK vault and pay them directly at 0% fee. Cost comes back in usage.cost_usd.
One call.
Many answers.
Same key and same balance as the chat models. BYOK with your own TypeSafe key routes at 0% fee. The welcome credit covers thousands of decisions.
Send a state
A ticket, a brief, a transcript, a JSON record. Text or JSON, up to about 32k tokens. It is sent once, whatever you ask about it.
Ask typed questions
noul is a yes/no probability. choice picks one label from criteria you describe. score places on a rubric you define, from zero. Ask several in one call.
Threshold the numbers
Answers are probabilities and distributions, never prose. Act above a threshold, hand to a human below it, and treat a noul near 0.5 as unsure.
Six patterns, ready to run.
Each one is a complete request you can run above, copy as cURL, Node or Python, or download as JSON. Edit the questions to fit your data; the shape stays the same.
Put a decision
in front of the spend.
POST /v1/decisions from your code, or let your agent call the decide tool on our MCP server before every expensive step.