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 status update to distinguish a dependency, unresolved scope or missing access. Keep absent or unclear blockers separate rather than assessing an employee or assigning a severity.
A frustrated tone does not establish a blocker. The fifth example explicitly says work continues. The other fixtures identify a missing artifact, an unresolved requirement and missing access as different obstacles.
The label can help a reviewer ask a focused follow-up: obtain the artifact, clarify the acceptance criteria or verify access. It does not identify who is responsible or assess the author’s performance.
The source suggests reviewing daily updates for follow-up. This original example preserves the report’s stated evidence and sends no message to a manager or colleague.
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 work blocker classification.

Read a status update to distinguish a dependency, unresolved scope or missing access.

Open the decision rules and keep the intended distinction between Dependency blocker, Scope blocker, Access blocker, No blocker stated, 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 |
|---|---|---|
| Waiting for schema | Dependency blocker | 100% |
| Unknown acceptance rule | Scope blocker | 98.0% |
| Permission missing | Access blocker | 100% |
| Routine progress | No blocker stated | 100% |
| Frustration without a blocker | No blocker stated | 100% |
| No update 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.
No. It only means the supplied complete update names no obstacle to continuation. Hidden problems remain outside the evidence.
Yes. These fixtures make one primary. For equally central blockers, extend the contract to preserve multiple outcomes instead of forcing one.
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.