Device room matching: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Provide device metadata and the existing room list. Choose a clearly stated kitchen, office or garage, keeping unknown and conflicting locations unmatched.
An area assignment should use the installation’s actual room list. A clear Bedroom label does not justify mapping to Office just because Bedroom is missing from that list.
This demonstration reads naming metadata, not location sensors. It leaves portable or ambiguously named devices unresolved and never writes the selected label into a real registry.
This original metadata-matching exercise adapts the area-choice question in ha-gutcheck, linked by the source post. The rooms and devices are fictional. It does not locate hardware, create rooms or change Home Assistant assignments.

Use the sample to understand the rule, then test your own input for device room matching.

Provide device metadata and the existing room list.

Open the decision rules and keep the intended distinction between Kitchen, Office, Garage, None. 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 uncertain or unexpected results before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Named kitchen device | Kitchen | 55.0% |
| Office workspace | None | 96.0% |
| Garage sensor | Garage | 88.0% |
| Model alone | None | 100% |
| Unlisted bedroom | None | 100% |
| Conflicting names | None | 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. 5 of 6 results matched the authored fixture expectations. For Office workspace, the expectation was Office; the observed choice was None.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.
Not under this rule. Supply a room-bearing description; common product use is not evidence of this installation’s location.
The result is None. An application can ask the user to create or select the right room separately, with permission to update the registry.
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.