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.
Paste a captured note to identify its stated purpose. Distinguish an action to carry out from a possibility or saved reference, keeping notes with two equally central purposes marked as mixed.
A proposal for a reminder tool contains send, but it is still an idea. The committed follow-up names work to carry out. That distinction matters when a capture inbox feeds a task list.
Reference material should remain available without becoming a to-do item. Mixed preserves a note that both records an explanation and assigns a follow-up, so the receiving application can split it deliberately.
This is an original intake example inspired by a discussion of organizing Telegram captures in Obsidian. It does not read either service or create notes in a vault.
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 note inbox classification.

Paste a captured note to identify its stated purpose.

Open the decision rules and keep the intended distinction between Task, Idea, Reference, Mixed, 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 |
|---|---|---|
| Committed follow-up | Task | 100% |
| Possible experiment | Idea | 100% |
| Saved documentation | Reference | 99.0% |
| Two purposes | Mixed | 99.0% |
| An idea containing an action word | Idea | 100% |
| No captured text | 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.
Yes. Quoted instructions in documentation can remain Reference when the note is explicitly saved for consultation. Purpose matters more than the presence of an imperative verb.
No. The label makes the two purposes visible. The application or user decides whether to split the capture.
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.