Jev conversation followup state

Check whether an exchange leaves a genuine follow-up question

Provide the last user and assistant messages. Distinguish an unanswered genuine question, an explicit ending and an exchange with no closing cue.

Does this exchange leave a follow-up open?Live API
Try an example

The assistant explicitly asks the user for a decision.

Source: API-collected workflow inspiration; original demonstration below

Source and example scope

The API-collected roundup links the cited project. Its pinned source defines the decision adapted here. These synthetic inputs and explicit missing-context outcomes are original to this demonstration. The window returns a label; it does not run the linked application, execute its downstream actions or verify its performance claims.

Read the last user and assistant messages.

Decision rules and labels
Open follow-upClosed exchangeNo closing cueNeed exchange
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

A question mark in a quotation does not make the conversation an open question.

The deployment preset asks the user to choose a region, so it leaves a real follow-up open. The terminal-output preset quotes Continue? while explaining that no answer is requested. The same punctuation serves a different purpose.

When the user ends the exchange but the assistant then asks a genuine question, this demonstration chooses Open follow-up. That priority follows the linked source’s two-check policy. It does not judge whether the additional question was appropriate.

The cache.warming source uses conversation cues as inputs to its cache policy. This original demonstration only classifies the supplied messages. It neither changes a cache nor predicts whether the user will return.

The API-collected roundup links the cited project. Its pinned source defines the decision adapted here. These synthetic inputs and explicit missing-context outcomes are original to this demonstration. The window returns a label; it does not run the linked application, execute its downstream actions or verify its performance claims.

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 conversation follow-up.

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

    Add the information to check

    Provide the last user and assistant messages.

  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 Open follow-up, Closed exchange, No closing cue, Need exchange. 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 Need exchange 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
A decision is requestedOpen follow-up100%
Explicit endingClosed exchange100%
Ordinary acknowledgmentNo closing cue99.0%
Question after an endingOpen follow-up100%
Quoted questionNo closing cue96.0%
User message absentNeed exchange74.0%

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

Understand the results

Replay the saved synthetic requests to inspect each recorded decision

Replay the saved synthetic requests to inspect each recorded decision. Authored expectations and model disagreements remain available; these examples are not a production accuracy benchmark.

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.

Runnable offline example

Run one sample, then inspect the local packet

View the code example
Single-request replay
npm install @typesafe-ai/sdk@0.6.0
# Set TYPESAFE_API_KEY privately in your shell.
node run-choice-sample.mjs samples.json case-1
python preview_choice_workflow.py samples.json saved-api-results.json
Scope of this demo

Where this decision fits

Useful scope

  • Inspecting the last pair of conversation messages
  • Separating genuine and quoted questions
  • Finding unresolved follow-ups after an ending

Outside this demonstration

  • Predicting whether a user will reply
  • Keeping a session or cache alive
  • Judging whether an assistant should ask another question
Example FAQ

Questions about conversation followup state.

Input scope and downstream handling determine what this judgment means.

Why does a question take priority over the user’s ending?

The linked decision checks for an assistant question before checking whether the user ended the conversation. This demonstration preserves that ordering as an explicit classification rule.

Does No closing cue mean the user wants to continue?

No. It means the supplied complete messages establish neither a genuine assistant question nor an explicit user ending. It is not a prediction of intent beyond those cues.

Is the leading probability an accuracy measurement?

No. It is one value in the returned distribution over this request’s choices. The six synthetic fixtures have authored expectations; they do not measure production accuracy.

What happens on an API failure?

The window displays an error without a fresh judgment. An incomplete-input outcome describes the supplied evidence and is not used as a fallback for provider failure.

Try your own conversation followup state input

Edit the input above, or open the Playground to explore another decision.