private demo · all data synthetic

Every row, every question, scored at once

A pile of rows plus any yes/no questions you write. Each row gets a 0 to 1 score per question (0 = no, 1 = yes), all in seconds, for pennies. You choose the cut line; your rules apply to the whole dataset.

Viewing precomputed results. Live scoring and generation need the invite link (it ends in ?key=...).

1 · data in

Pick, paste or generate the rows

Presets are scored already, so switching is instant. Synthetic data from datasets.js; scores precomputed through the live function.

Gemini flash-lite writes the rows (synthetic, no real people); if it fails the built-in template generator is used instead. One generation per minute.

2 · ask

Yes/no questions (up to 6)

what this is

Jev (TypeSafe) is a model that does not write text. It answers typed questions about any text with a calibrated 0 to 1 confidence, about a quarter of a second and about $0.00002 per row. That makes it practical to run policy questions ("is this fraud?", "would this leak data?") across every row of a dataset or every action of an agent, and let code, not the model, decide what happens at each threshold. The key for Jev lives only in the serverless function; nothing you paste is stored. Sources: TypeSafe API · Confidence · jev-1.13 on OpenRouter · gating agent tool calls · independent evaluation.

Step 1 of 3

Data in

Start with a pile of rows: 300 bank cases here. Paste your own or generate some later.