Ask once. Read every document.
Prepare your documents and questions, then let Jev classify them together.
Documents
Prepared locally in your browser
Add your documents
Prepared document text
0 readyThis is the state Jev will read. One document per request.
Add a file or paste text to inspect what Jev will receive.
View request state as JSON
Questions
Write new questions or reuse a saved set
What do you want to know?
Have answer choices? Paste the question and all its options into one box. Ordered rubrics are kept as choices unless you request a numeric score.
Answer bullets stay with their question, including across blank lines. For exact boundaries, put %%% between complete questions.
Check each question and its options. Edit below or merge a split. To split further, insert %%% in the original text and preview again.
Study context & document context optional
When checked, document titles and the first 2,500 characters of the first document also go to the selected language model.
Sends questions + study context + Jev format rules.
Question conversion connects directly to your chosen provider. Keep the app open while a request is running; completed work is saved on this device.
Pick up where you left off.
Load a questions JSON file directly into the review area. No language model or conversion key required. Loaded questions are added to your current set.
Jev questions
0 readyApproval is optional. All included questions with valid formatting can run. Incomplete questions are skipped.
Convert English questions, load JSON, or .
Save your question set now. No Jev run required.
Ready to run with Jev?
Jev receives each document’s text and your prepared questions.
Every document. Every answer.
Compare classifications and inspect their probabilities.
Your results will appear here.
Add documents and prepare questions, then run with Jev.
Classification results
Choose Show probabilities for the full breakdown, or hover a cell. Scores are expected values and can fall between rubric levels; a value near the midpoint between two levels means the document sits close to that boundary.