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.
Compare every stated precondition with the target setup. Separate satisfied requirements, explicit conflicts and unresolved conditions before reusing the workflow; an absent condition is not automatically fulfilled.
A workflow that succeeded earlier may require a specific format or permission boundary. The target notes must establish those conditions before its earlier success becomes relevant to the new run.
Condition unresolved preserves a missing confirmation without calling it a conflict. No stated conditions means the saved procedure does not expose the assumptions needed for this check; it is not automatic permission to run.
The source describes surfacing reusable workflows from agent history. This adaptation reviews stated preconditions only. It does not connect to a harness or verify that the saved procedure works.
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 workflow reuse conditions.

Compare every stated precondition with the target setup.

Open the decision rules and keep the intended distinction between Preconditions satisfied, Precondition conflict, Condition unresolved, No stated conditions, 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 |
|---|---|---|
| Matching format | Preconditions satisfied | 100% |
| Format conflict | Precondition conflict | 100% |
| Permission unresolved | Condition unresolved | 100% |
| Conditions not defined | No stated conditions | 99.0% |
| One satisfied, one failed | Precondition conflict | 100% |
| Missing target setup | Need evidence | 77.0% |
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
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 means there are no declared preconditions to inspect in the supplied workflow. A reviewer may need to document them before reuse.
A saved decision answers a particular question. A workflow is a procedure with execution assumptions; this check compares those assumptions with the target setup.
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.