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.
Read a feedback note to distinguish wording, visual and interaction changes. Preserve equally requested mixed edits before planning the work; the result does not identify a project owner.
Brighter appears in the proposed headline, but the client requests wording only. The classifier follows the requested edit rather than interpreting an adjective as a design instruction.
Mixed edit keeps equal layout and validation work together for review. Splitting that note into implementation tasks is a separate application step that needs the project and relevant files.
The source describes an email-to-issue workflow. This adaptation classifies a note’s edit type; it does not create a Linear issue, edit a site or open a pull request.
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.

Use the sample to understand the rule, then test your own input for website feedback types.

Read a feedback note to distinguish wording, visual and interaction changes.

Open the decision rules and keep the intended distinction between Copy edit, Visual edit, Behavior edit, Mixed edit, Need evidence. Edit the choices only when testing your own rule.

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

Review Need evidence before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Button wording | Copy edit | 100% |
| More spacing | Visual edit | 100% |
| New filter behavior | Behavior edit | 100% |
| Layout plus behavior | Mixed edit | 100% |
| Visual words in copy | Copy edit | 100% |
| No requested change | Need evidence | 100% |
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
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.
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.
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.jsonThe rubric explains the decision; the application owns the next step.
No. It classifies the requested edit. Project assignment needs the client, project context and ownership evidence.
Yes. Visual describes the requested outcome, not the file type. A CSS or component edit can still be Visual edit when interaction behavior stays unchanged.
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.
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.
Edit the evidence above or use the Playground to test another bounded question.