Jev focus page intent

Check whether a page supports your current focus goal

Describe the current redacted page and the task you chose. Compare task-serving content with an unrelated feed or other purpose, even within the same website.

focus page intentLive API
Try an example

The actual lesson supports the stated goal.

Source: API-collected workflow inspiration; original demonstration below

Source and example scope

This is an independently authored text demonstration inspired by the linked X discussion. Its rules and synthetic inputs are ours. It does not reproduce the author’s application, verify reported outcomes, or perform an external action.

Compare the current redacted page with the stated focus goal.

Decision rules and labels
Task servingUnrelated feedOther unrelatedReview
A real response from the Jev API

Edit any input to explore a different decision. No request is sent until you run it.

Your next decision

Not run yet

Choose an example or write your own input, then run it to see the ranked choices.

Results are not stored by this site. Your submitted text is processed by the API provider.

The decision

What the decision checks

A focus rule needs the user's chosen task. Calling an entire video site distracting would also hide lectures that support that task, while a relevant-looking domain can still show unrelated recommendations.

Use redacted text and explicit surface descriptions. This page has no browser access, screen capture or session history; its result only describes the evidence entered into the form.

Qualm describes task-aware screen-time intervention and distinguishes work or learning from feeds. This original text adaptation demonstrates the relevance question only, without monitoring, blocking or recording a real browsing session.

This is an independently authored text demonstration inspired by the linked X discussion. Its rules and synthetic inputs are ours. It does not reproduce the author’s application, verify reported outcomes, or perform an external action.

Illustration of one spreadsheet row producing two separate classification results
Illustration of the decision flow.
How it works

Try the example in four steps

Use the sample to understand the rule, then test your own input for page relevance to a goal.

  1. Illustration of adding the text or evidence for a decision

    Add the information to check

    Describe the current redacted page and the task you chose.

  2. Illustration of defining a question and its allowed choices

    Confirm the question and labels

    Open the decision rules and keep the intended distinction between Task serving, Unrelated feed, Other unrelated, Review. Edit the choices only when testing your own rule.

  3. Illustration of sending one input and comparing the returned choices

    Run the decision

    Use a sample first, then try your own input. Compare the selected label with the other returned probabilities.

  4. Illustration of reviewing a result and an uncertain item before using it

    Review the next step

    Review Review before using a result. The label is a decision about the supplied information, not an executed action.

Our API test

Recorded API observations

Recorded API observations
Original inputObserved labelLeading probability
A relevant lectureTask serving100%
Same site, unrelated feedUnrelated feed98.0%
Unrelated purchase pageOther unrelated99.0%
Working referenceTask serving93.0%
No goal suppliedReview91.0%
Title without contentReview70.0%

These are six original synthetic inputs, tested once per request revision. The percentage is the leading option probability, not measured accuracy. Authored expectations and any disagreements remain in the downloadable evidence. 6 of 6 results matched the authored fixture expectations.Verified

Understand the results

Page relevance to a goal: six recorded examples

The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.

Using the result in your application

The single-request SDK runner uses your private TYPESAFE_API_KEY. The offline consumer reads saved observations, checks request hashes and prints a pending output. It does not call the model or change any external system.

Replay options

Inspect saved outputs or request a new decision

View the code example
Two independent commands
# Offline: inspect the downloaded saved observations. No API key is needed.
python preview_choice_workflow.py samples.json saved-api-results.json

# Optional live request: install the SDK and set TYPESAFE_API_KEY privately.
npm install @typesafe-ai/sdk@0.6.0
node run-choice-sample.mjs samples.json case-1
# The live response prints to the terminal; it does not update saved-api-results.json.
Scope of this demo

Where this decision fits

Useful scope

  • Testing a task-aware reading or focus prompt.
  • Comparing a lecture and an unrelated feed on the same site.
  • Explaining why the focus goal must be supplied before judging a page.

Outside this demonstration

  • Inferring a person's attention or productivity from a label.
  • Sending private screen content or closing tabs without a separate consent policy.
Example FAQ

Using this example

The input contract and these limits define what the result means.

Does the page monitor my browsing?

No. You provide the goal and redacted page description. There is no browser extension or background screen access in this demonstration.

Can entertainment be task serving?

Yes, when the stated task actually calls for it, such as studying a specific comedy scene. The judgment is about the supplied goal, not a universal list of good and bad websites.

Does the leading probability measure accuracy?

It describes the distribution over the supplied choices for this request. These six synthetic examples are functional tests with authored expectations, not a production accuracy benchmark.

Will a result change an external system?

No. The demo displays a label and distribution. The downloadable consumer produces a pending preview packet. Application code and a separate authorization policy would control any real action.

Test a different input

Edit the example above to see how a changed fact affects the decision, or open the Playground for another task.