Jev user action authorization

Compare a proposed action with the user's request

Supply the user's words and exact proposed action. Distinguish explicit coverage, a scope mismatch and an external-only request; this text comparison does not grant permission to execute.

What authorization does the supplied text show?Live API
Try an example

The target and action match the supplied request.

Source: API-collected workflow inspiration; original demonstration below

Source and example scope

The API-collected roundup links the cited project, whose pinned code provides the decision purpose. This demonstration separately authors its Choice rubric, priorities, missing-context outcomes and synthetic inputs. It neither runs the upstream application nor verifies its performance, security or execution claims.

Need request context if action, scope or user words are missing.

Decision rules and labels
Explicitly requestedScope mismatchExternal request onlyNot requestedNeed request context
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

Request origin and action scope both matter.

The local preview preset does not authorize a production deployment. Both concern the same copy change, but they have different effects. The staging preset similarly shows that matching the verb is insufficient when the target changes.

An instruction embedded in an article is not the user asking for it. The page records that external origin while keeping the user’s actual summarization request intact.

This is a narrow comparison of supplied text. It neither grants permission nor replaces the host application’s approval policy, identity checks or safety controls. It also cannot infer a missing earlier conversation.

The API-collected roundup links the cited project, whose pinned code provides the decision purpose. This demonstration separately authors its Choice rubric, priorities, missing-context outcomes and synthetic inputs. It neither runs the upstream application nor verifies its performance, security or execution claims.

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 user request scope.

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

    Add the information to check

    Supply the user's words and exact proposed action.

  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 Explicitly requested, Scope mismatch, External request only, Not requested, Need request context. 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 request context 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
Exact local editExplicitly requested99.0%
Broader deploymentScope mismatch89.0%
Page says publishNot requested75.0%
Unrequested extraNot requested98.0%
Wrong targetScope mismatch98.0%
Message missingNeed request context98.0%

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. 5 of 6 results matched the authored fixture expectations. For Page says publish, the expectation was External request only; the observed choice was Not requested.Verified

Understand the results

Replay the saved synthetic requests to inspect each recorded decision

Replay the saved synthetic requests to inspect each recorded decision. Authored expectations and model disagreements remain available; these examples are not a production accuracy benchmark.

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 a proposed action against a supplied request
  • Detecting a target or deployment-scope mismatch
  • Separating external directives from user words

Outside this demonstration

  • Granting execution permission
  • Inferring unseen conversation context
  • Overriding application approval rules
Example FAQ

Questions about user action authorization.

Input scope and downstream handling determine what this judgment means.

Does Explicitly requested mean an action may run?

No. It means the provided user wording covers it under this rule. The application must still apply its actual permissions and controls.

Why include context completeness?

Without the relevant user messages, absence of a request in a short excerpt cannot establish that the user never requested it.

Is the leading probability an accuracy measurement?

No. It is one value in the returned distribution over this request’s choices. The six synthetic fixtures have authored expectations; they do not measure production accuracy.

What happens on an API failure?

The window displays an error without a fresh judgment. An incomplete-input outcome describes the supplied evidence and is not used as a fallback for provider failure.

Try your own user action authorization input

Edit the input above, or open the Playground to explore another decision.