Agent request grouping: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Paste a handover message to distinguish one coherent choice from independent requests. A list of alternatives can still belong to the same decision.
This check identifies the decisions inside a message. Sentence count is a poor substitute: a five-sentence release summary can contain one approval, while two short sentences can ask for unrelated choices.
The linked project uses Jev to inspect agent handovers. This original example exposes one part of that pattern with new labels and inputs. It does not install a hook, rewrite the message or block an agent.
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 agent request grouping.

Paste a handover message to distinguish one coherent choice from independent requests.

Open the decision rules and keep the intended distinction between No request, One decision, Separate requests, 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 |
|---|---|---|
| Deployment report | No request | 100% |
| One region choice | One decision | 100% |
| Independent topics | Separate requests | 100% |
| One release approval | One decision | 100% |
| Missing proposal | Review | 82.0% |
| Two yes-no choices | Separate requests | 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.
# 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.
No. Frankfurt, Dublin or Paris are alternatives for one region choice. Separate requests must be independently answerable decisions.
No. Its length does not determine the label. A detailed explanation may support one coherent approval.
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.