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.
Gate an ad or a landing page before spending on copy and media.
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.
The gate is the cheapest step, so it runs first; generation only happens on a pass.
What to do with the numbers
- claim_risk ≥ 1.5 → stop. Rewrite the hook before any copy or media is generated.
- worth_making < 0.7 → skip with reasons; no money page, no video.
- Only a pass reaches the chat model for copy and the media model for stills.
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": "Product: collapsible desk organizer, plastic, 4 trays, ships from EU warehouse, €24. Hook idea: '\''Doctors say a clean desk cures anxiety, this one pays for itself in a week.'\''",
"questions": {
"worth_making": {
"type": "noul",
"instructions": "Would this convert as a short-form ad for a cold viewer?",
"criteria": {
"true": "Clear product, believable buyer, specific benefit",
"false": "Vague, saturated, or nothing to show"
}
},
"claim_risk": {
"type": "score",
"instructions": "How risky are the implied claims?",
"criteria": [
"Ordinary retail claims",
"Hype that needs softening",
"Medical, income or guarantee claims: do not publish"
]
},
"hook": {
"type": "choice",
"instructions": "Best first hook for this product?",
"criteria": {
"problem": "Show the messy desk first",
"demo": "Show it folding and unfolding",
"social_proof": "A reviewer'\''s reaction",
"unbox": "First look out of the box"
}
}
}
}'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.