Video progress indicator: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Describe the video's structure to compare staged explanations with self-contained reactions or punchlines. Choose a show, hide or unclear preference without using duration alone or editing the video.
A progress indicator can help viewers place a step within a sequence. This example asks about that orientation need rather than assuming that every long clip needs a bar or every short clip should omit one.
The model sees the text you supply. Playback timing, screen layout and accessible presentation belong in the player or renderer. The result makes no claim about retention or completion rates.
This independently authored text exercise adapts an edit decision defined in the linked Jev Shorts Editor repository. Its synthetic shots, simplified rules and missing-input outcomes are original to this page. It does not reproduce a rendered edit, inspect video, or verify the repository’s timing and cost claims.

Use the sample to understand the rule, then test your own input for video progress indicator.

Describe the video's structure to compare staged explanations with self-contained reactions or punchlines.

Open the decision rules and keep the intended distinction between Show, Hide, Unclear. 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 Unclear before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Setup walkthrough | Show | 100% |
| Numbered advice | Show | 100% |
| Single reaction | Hide | 100% |
| Single claim | Hide | 100% |
| Length only | Unclear | 99.0% |
| Short but staged | Show | 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
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
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 input contract and these limits define what the result means.
No. The rule uses structure. A long unstructured reaction still differs from a sequence of steps.
Those are outside this request. The output only addresses whether progress orientation is useful for the described content.
It describes the distribution over the supplied choices for this request. These six synthetic examples are functional tests with authored expectations, not a production accuracy benchmark.
No. The demo displays a label and distribution. The downloadable consumer produces a pending preview packet. Application code and a separate authorization policy would control any real action.
Edit the example above to see how a changed fact affects the decision, or open the Playground for another task.