Independent guideAn independent guide to Jev by TypeSafe AI
Use cases

One focused check for a draft

Check product writing for absolute promises

Use a Jev yes/no writing-check template to flag absolute promises, then review the wording and its context yourself.

Load this template

Sources reviewed Updated Content revision 1

Evidence Original fictional teaching example. No model result is prefilled.

Original fictional teaching example. No model result is prefilled.

An editable starting point

Load this template
1 · Text to check
Orbit Notes saves drafts on your device. Click Export to download a copy.
2 · Your question
Does it make an absolute promise without stated limits?
When does Yes apply?
The text promises an outcome always happens, cannot fail or has no exceptions.
When does No apply?
The text gives conditions or limits, or makes no guarantee.

These are model probabilities, not measured accuracy or a guarantee. Yes and No describe your rules; choices are relative to the options you supplied.

The task

Before publishing product copy, identify sentences that promise an outcome without stated limits. This recipe asks one Noul question about absolute promises. It is not a general writing grade, a factual audit, or a test of who wrote the text.

The fictional material and rules are original teaching examples. They are not Every’s prompt or a reproduction of its experiment. The single-question custom template differs from the illustrated writing scenario, which contains several checks. No model response is prefilled.

Change one thing at a time

Load the template, inspect the yes and no rules, and replace the example with a short, non-sensitive draft. First try a bounded description of a feature. Then change only one sentence into an unconditional guarantee. State whether quoted claims, negated guarantees, and limits in the following sentence count for your editorial policy.

Keep the question narrow. If you also care about repetition or a clear next step, review those separately rather than combining them into “Is this good writing?”

What the probability means

For this question, a higher yes probability means the model judges that the defined promise is present. It does not mean the draft is better. Return to the actual sentence and verify what it promises, to whom, and under what conditions. Jev does not rewrite the copy or establish that a claim is true.

Inspect a difficult example

A sentence can quote a customer’s “always works” claim and then explicitly reject it. A keyword match would flag the phrase; your intended rule may not. Compare that example with the same words used as the product’s own promise. Decide the intended judgments before looking at the model’s suggestions.

Continue with Choice versus Noul to choose the right question type. These are suggested editing exercises, not an independently measured accuracy test.

Sources & further reading

Official documentation and linked community reports support this guide. Community observations are attributed to their authors.

  1. TypeSafe: Noul
How we check our sources