Book subject tagging: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Give a proposed tag, its rule and a book description or excerpt. Compare substantive support with excluded content and a suggestive title that needs review.
A tag is a rule, not just a word. Include exclusions when a name has common metaphorical or adjacent meanings.
This one-tag Choice demo adapts a library-tagging pattern. It does not implement the source plugin’s multiple independent tag questions, thresholds or calibre integration.
Use original or permitted excerpts and review suggestions before updating a catalog. A short excerpt may not represent the entire book.
This is an independently authored text demonstration inspired by the linked X discussion. Its rules and synthetic inputs are ours. It does not reproduce the author’s application, verify reported outcomes, or perform an external action.

Use the sample to understand the rule, then test your own input for book subject tagging.

Give a proposed tag, its rule and a book description or excerpt.

Open the decision rules and keep the intended distinction between Supported, Excluded, Review. 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 |
|---|---|---|
| Practical programming | Supported | 100% |
| Career memoir | Excluded | 100% |
| Ambiguous title | Review | 100% |
| Fictional mystery | Supported | 99.0% |
| Different meaning | Excluded | 100% |
| Conflicting metadata | Review | 56.0% |
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.
Yes. This exercise checks one tag at a time. Separate subject and genre tags may both fit; a complete application needs its own multi-tag selection policy.
Not in these samples. Reusing unverified tags can simply repeat an earlier classification mistake.
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.