Jev event intent evidence

Review event behavior against an acceptable-use policy

Give an event's purpose, verified behavior notes and policy. Distinguish routine evidence, prohibited behavior and conflicting or inconclusive signals before a separate enforcement decision.

What do the supplied signals support?Live API
Try an example

Original input for the Routine evidence outcome. Edit the evidence to send a new request.

Source: Background discussion on X

Source and example scope

These fictional inputs and decision rules were written for this page. The linked X discussion provides background; the technical implementation follows TypeSafe's Choice contract.

Read stated purpose and verified behavior notes.

Decision rules and labels
Routine evidenceAbuse evidenceConflicting signalsInconclusiveNeed evidence
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

A suspicion label is not a verified behavior.

The suspicious-click fixture checks a misleading name against ordinary behavior notes. The rule relies on stated evidence, so a dramatic identifier does not establish abuse.

Conflicting signals preserves a record with both ordinary and prohibited behavior. Inconclusive keeps a sparse observation visible without treating missing evidence as innocence or guilt.

This toy record does not expose a real detection method or assess a visitor’s identity. WAF, rate limits and authorization remain separate controls. The model label is only a pending review signal.

These fictional inputs and decision rules were written for this page. The linked X discussion provides background; the technical implementation follows TypeSafe's Choice contract.

Illustration of reviewing messages against supplied policy categories
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 event-policy evidence.

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

    Add the information to check

    Give an event's purpose, verified behavior notes and policy.

  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 Routine evidence, Abuse evidence, Conflicting signals, Inconclusive, Need evidence. 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 Need evidence 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
Ordinary usageRoutine evidence100%
Explicit prohibited behaviorAbuse evidence95.0%
Conflicting recordConflicting signals96.0%
Sparse observationNeed evidence52.0%
Suspicious name aloneRoutine evidence48.0%
No policy or signalsNeed evidence100%

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. 5 of 6 results matched the authored fixture expectations. For Sparse observation, the expectation was Inconclusive; the observed choice was Need evidence.Verified

Understand the results

Source and example scope

Compare each saved result with its authored expectation. A disagreement remains in the fixture review; the call is not repeated to obtain a preferred label.

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.

Runnable offline example

Run one sample, then inspect the local packet

View the code example
Single-request replay
npm install @typesafe-ai/sdk@0.6.0
# Set TYPESAFE_API_KEY privately in your shell.
node run-choice-sample.mjs samples.json case-1
python preview_choice_workflow.py samples.json saved-api-results.json
Scope of this demo

Where this decision fits

Useful scope

  • Reviewing fictional interaction evidence against a policy
  • Separating suspicion from an established prohibited action
  • Replaying the exact synthetic requests and inspecting their distributions

Outside this demonstration

  • Blocking users from a sparse semantic label
  • Inferring protected traits or private intentions
  • Treating six fixture expectations as measured production accuracy
Example FAQ

Questions about event intent evidence.

The rubric explains the decision; the application owns the next step.

Is Routine evidence a safety guarantee?

No. It means the supplied notes describe routine use under the given policy. Hidden behavior and incomplete telemetry remain outside the input.

Should Conflicting signals be discarded?

No. Preserve the whole record for review. The example deliberately avoids hiding an observed prohibited signal behind ordinary activity.

Does the leading probability measure production accuracy?

No. It is the model distribution for this one request. The six examples are functional checks with authored expectations, not a representative benchmark. Inspect disagreements and evaluate your own examples before using the label.

What happens when the API fails?

The window shows an error and supplies no fresh judgment. The downloadable runner sends one request without retries. Need evidence is a valid outcome about incomplete input; it does not stand in for a network or provider failure.

Try your own event intent evidence input

Edit the evidence above or use the Playground to test another bounded question.