Mobile search next step: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Provide the goal, visible search state and available operations. Choose a permitted next step such as focus, type, submit or wait; the example returns a label rather than controlling a device.
This task uses structured observations: focus, current text, submission state, loading and visible results. It does not infer screen contents from a screenshot or assume that an action succeeded because it was requested.
The page returns a proposed operation from the offered set. A real controller still needs permission checks, an executor and an independent readback. Done here describes the supplied observation, not a verified device run.
This original text demonstration adapts a decision in a repository linked by the cited X post. The examples and explicit uncertainty outcomes are ours. The post is a directory reference, not proof that its author built every linked project. No third-party benchmark, business outcome or external action is reproduced.

Use the sample to understand the rule, then test your own input for mobile search next step.

Provide the goal, visible search state and available operations.

Open the decision rules and keep the intended distinction between Focus, Type, Submit, Wait, Done. 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 Review before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Field not focused | Focus | 97.0% |
| Ready to enter text | Type | 98.0% |
| Entered but not sent | Submit | 99.0% |
| Loading response | Wait | 99.0% |
| Results verified | Done | 96.0% |
| Success not observed | Review | 91.0% |
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
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.
# Offline: inspect the downloaded saved observations. No API key is needed.
python preview_choice_workflow.py samples.json saved-api-results.json
# Optional live request: install the SDK and set TYPESAFE_API_KEY privately.
npm install @typesafe-ai/sdk@0.6.0
node run-choice-sample.mjs samples.json case-1
# The live response prints to the terminal; it does not update saved-api-results.json.The input contract and these limits define what the result means.
An otherwise sensible step may be unsupported in the current state. The rule selects only an offered operation or returns Review.
No. The supplied observation must show the matching results. An executor should obtain that readback independently.
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.