Use Cases / image-presence-gate
Jev Image Presence Gate (beta)
Image inputs and Box questions are beta and dreamer-ready, not recommended for production. Sometimes you only need a yes/no: is a badge, logo, or warning visible — not a full bounding box.
Try a related template free on this host — 5 anonymous real-API runs with no signup — then ship the same schema with a prepaid jv_live_ key. See is Jev free? and playground.
Why Jev
Attach image assets and ask a noul (or choice) over the image. You get a calibrated probability your code can threshold — still experimental multimodality, not a replacement for trained classifiers.
How to define the decision
assets.frame = { type: "image", format: "png", data_base64: "…" }. questions.visible = { type: "noul", instructions: "Is a warning badge visible in frame?" }. Optionally add a box question for the same asset.
When to use Jev
- Prototype “is X visible?” gates
- Pairing a presence Noul with a follow-up box question
- Eval harnesses comparing text-only vs image-augmented asks
When not to use Jev
- Safety-critical allow/block in production
- Fine-grained multi-label taxonomy at scale
- Video streams
Failure modes and human fallback
- Upstream or network errors: retry with backoff; do not invent a decision.
- Low confidence: route to a human queue or safer default — never auto-act on money/destructive tools.
- Schema drift: keep a golden fixture set in CI so label changes fail the build before production.
- Official: Image inputs and Box questions are beta and dreamer-ready, not recommended for production.
- Image tokens still meter as input when you call the live API.
- Prefer dedicated vision classifiers for production presence detection.
API example
Same prepaid jv_live_ balance as tools. Output tokens are free on this host's metering model.
curl https://jevtypesafe.org/api/v1/decide \
-H "Authorization: Bearer jv_live_YOUR_KEY_HERE" \
-H "Content-Type: application/json" \
-d '{"state":"Customer: I've been waiting five days for my refund.","questions":{"action":{"type":"choice","instructions":"Decide the next step","criteria":{"allow":"safe","review":"unsure","block":"unsafe"}}}}'FAQ
- Is this safer than box for production?
- No. Image inputs (and Box) remain beta and dreamer-ready — not recommended for production either way.
- Can I combine noul and box?
- Yes — same decide call can include both question types over shared assets. Still experimental.
Related use cases
Ready to build?
Free anonymous tool runs, then prepaid packs and a jv_live_ key — independent host, not affiliated with TypeSafe AI.