Jev agent request unpacking

Check whether an agent message asks for separate decisions

Paste a handover message to distinguish one coherent choice from independent requests. A list of alternatives can still belong to the same decision.

agent request unpackingLive API
Try an example

Three facts do not make three requests.

Source: API-collected workflow inspiration; original demonstration below

Source and example scope

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.

Classify what the agent asks the user to decide.

Decision rules and labels
No requestOne decisionSeparate requestsReview
A real response from the Jev API

Edit any input to explore a different decision. No request is sent until you run it.

Your next decision

Not run yet

Choose an example or write your own input, then run it to see the ranked choices.

Results are not stored by this site. Your submitted text is processed by the API provider.

The decision

What the decision checks

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.

Illustration of choosing one tool from the supplied alternatives
Illustration of the decision flow.
How it works

Try the example in four steps

Use the sample to understand the rule, then test your own input for agent request grouping.

  1. Illustration of adding the text or evidence for a decision

    Add the information to check

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

  2. Illustration of defining a question and its allowed choices

    Confirm the question and labels

    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.

  3. Illustration of sending one input and comparing the returned choices

    Run the decision

    Use a sample first, then try your own input. Compare the selected label with the other returned probabilities.

  4. Illustration of reviewing a result and an uncertain item before using it

    Review the next step

    Review Review before using a result. The label is a decision about the supplied information, not an executed action.

Our API test

Recorded API observations

Recorded API observations
Original inputObserved labelLeading probability
Deployment reportNo request100%
One region choiceOne decision100%
Independent topicsSeparate requests100%
One release approvalOne decision100%
Missing proposalReview82.0%
Two yes-no choicesSeparate requests100%

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

Understand the results

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.

Using the result in your application

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.

Replay options

Inspect saved outputs or request a new decision

View the code example
Two independent commands
# 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.
Scope of this demo

Where this decision fits

Useful scope

  • Reviewing an agent handover before displaying it
  • Distinguishing one multiple-choice question from several requests
  • Keeping status reports out of an approval queue

Outside this demonstration

  • Counting words or sentences
  • Deciding whether the requested action is authorized
  • Automatically rewriting or sequencing a conversation
Example FAQ

Using this example

The input contract and these limits define what the result means.

Are three options three requests?

No. Frankfurt, Dublin or Paris are alternatives for one region choice. Separate requests must be independently answerable decisions.

Does a long message always need splitting?

No. Its length does not determine the label. A detailed explanation may support one coherent approval.

Does the leading probability measure accuracy?

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.

Will a result change an external system?

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.

Test a different input

Edit the example above to see how a changed fact affects the decision, or open the Playground for another task.