JEV is INSANE. We gave it 700 high-intent leads and personalised outreach messages. In 40 seconds, it predicted how each message would perform, assigned a confidence score and detected lead-message mismatches. All for just $0.09. JEV can also score leads, analyse buying Show more
Choice
Pick one option from a set you define. Returns the option, the full probability distribution, and 0-1 confidence, with up to 255 options and parallel questions that barely add latency.
- Category
- Practices & Patterns
- Published by
- TypeSafe AI
- Author
- —
- Added
- 2026-09-20
Tagsofficialprimitiveschoiceconfidenceclassification
Highlights
- Option names and descriptions are both sent to the model; use null when a name speaks for itself.
- An ambiguous ticket example reads returns 0.61 vs billing 0.35 with confidence 0.42.
- Ask several Choice questions per call: they run in parallel and response time barely changes.
- Chain choices level by level for deep hierarchies, as in the hierarchical classification cookbook.
Quickstart
python
Choice(
instructions="Which team should handle this?",
criteria={
"returns": "Exchanges, wrong or damaged items",
"shipping": "Delivery status, delays, lost packages",
"billing": "Charges, invoices, payment problems",
},
)Watch out
Speculative questions still cost tokens even when your code ignores their answers, so weigh extra options against the input bill.
More like this
The yes/no primitive: one probability from 0 to 1, where the value is the answer and no separate confidence is needed. True and false criteria pin down subtle boundaries.
Practices & Patterns#official#primitives#noul
Official
Rate content against 2 to 10 ordered levels. Returns a probability-weighted score that can land between levels, per-level probabilities, and confidence, with the arithmetic left to code.
Practices & Patterns#official#primitives#score
Official
Use the answer to decide what to do and confidence to decide whether to act: the voice-banking example routes below 0.6 to a human and needs 0.85 or more to auto-approve a transfer.
Practices & Patterns#official#patterns#confidence
Official
From the community
Posts from builders shipping with Jev right now.
700 leads scored for $0.09
Beating Gemini Flash Lite on an eval
Ran @typesafeai's Jev against an existing classifier eval that previously used Gemini 2.5 Flash Lite. It won both on quality (saturated the eval) and speed (6x)
