Jev design operand kind

Identify what a design instruction changes

Give a design instruction to distinguish a whole object, displayed text and a property. Naming a shape does not make every requested edit an object operation.

What does this edit act on?Live API
Try an example

The whole circle moves.

Source: API-collected workflow inspiration; original demonstration below

Source and example scope

The API-collected studio roundup links this project. Its pinned implementation supplies the decision vocabulary discussed here. The six inputs and handling rules are original synthetic examples. This window returns a Choice label; it does not run the linked application or reproduce its speed, cost or output-quality claims.

Classify what the instruction directly edits.

Decision rules and labels
ObjectText contentPropertyNeed operand
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

Removing words is different from deleting their container.

“Remove the words from the button” should reach a text handler while preserving the button. “Delete the button” acts on the entire object. Both mention the same component, but require different work.

An independent text layer is itself an object. The object choice therefore covers creating that layer, while editing words inside an existing rectangle belongs to Text content.

This demo classifies one instruction. It does not inspect the canvas, resolve a selected node or execute an edit. Split a request with different operand kinds before passing it to separate handlers.

The API-collected studio roundup links this project. Its pinned implementation supplies the decision vocabulary discussed here. The six inputs and handling rules are original synthetic examples. This window returns a Choice label; it does not run the linked application or reproduce its speed, cost or output-quality claims.

Illustration of checking a code change and reviewing a flagged line
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 design edit targets.

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

    Add the information to check

    Give a design instruction to distinguish a whole object, displayed text and a property.

  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 Object, Text content, Property, Need operand. 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 operand 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
Move the circleObject99.0%
Replace its wordsText content100%
Change the fillProperty100%
Remove a labelText content100%
Two operand kindsNeed operand97.0%
No instructionNeed operand97.0%

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

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

  • Dispatching an instruction to an editor handler
  • Separating a label from its container
  • Detecting instructions that need splitting

Outside this demonstration

  • Editing a Figma file
  • Selecting an unseen canvas node
  • Executing several mixed edits
Example FAQ

Questions about design operand kind.

Input scope and downstream handling determine what this judgment means.

Is an independent text layer Text content?

Creating or deleting the whole independent layer is an Object operation under this rubric. Text content refers to the words on an existing shape or component.

Does a circle mentioned in the sentence force Object?

No. “Change the words inside the circle” acts on displayed text.

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 design operand kind input

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