Jev stop reply reaction

Read what a user wants after an agent stops

Compare the stopped work and user's reply. Distinguish a request to continue, a correction, a question, a new task and acknowledgment without executing the next action.

What does this follow-up ask for?Live API
Try an example

The reply asks for the already-requested action.

Source: API-collected workflow inspiration; original demonstration below

Source and example scope

The API-collected roundup links the cited project, whose pinned code provides the decision purpose. This demonstration separately authors its Choice rubric, priorities, missing-context outcomes and synthetic inputs. It neither runs the upstream application nor verifies its performance, security or execution claims.

Classify the reply to the agent stop.

Decision rules and labels
Continue existingCorrectionQuestionNew taskAcknowledgmentNeed 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

The same short reply can mean different things in different exchanges.

“Please do the fix I requested” continues unfinished work when the agent stopped at an offer. “That is the wrong environment” corrects a reported mistake. Those replies should not be collapsed into the same generic follow-up label.

The new-task preset explicitly accepts completion before requesting a table of contents. Without the earlier exchange, a phrase such as “do that next” leaves both the target and the intended continuation unclear.

The source hook uses conversation reactions to examine agent stops. This original Choice window classifies six synthetic exchanges. It does not monitor a conversation, resume an agent or infer whether the claimed test run really passed.

The API-collected roundup links the cited project, whose pinned code provides the decision purpose. This demonstration separately authors its Choice rubric, priorities, missing-context outcomes and synthetic inputs. It neither runs the upstream application nor verifies its performance, security or execution 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 replies after an agent stop.

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

    Add the information to check

    Compare the stopped work and user's reply.

  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 Continue existing, Correction, Question, New task, Acknowledgment. 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
Stopped at an offerContinue existing100%
Wrong destinationCorrection100%
Ask about evidenceQuestion100%
Move to another taskNew task100%
Simple thanksAcknowledgment100%
Missing prior messageContinue existing69.0%

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. 5 of 6 results matched the authored fixture expectations. For Missing prior message, the expectation was Need exchange; the observed choice was Continue existing.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

  • Reviewing synthetic stop-and-reply exchanges
  • Distinguishing unfinished work from a new request
  • Identifying missing context in short follow-ups

Outside this demonstration

  • Automatically executing a classified reply
  • Verifying an agent’s completion claim
  • Inferring an unseen conversation
Example FAQ

Questions about stop reply reaction.

Input scope and downstream handling determine what this judgment means.

Why does Correction take priority over Continue existing?

A reply can both point out a mistake and ask for work to continue. The rule preserves the explicit error signal as the primary label.

Does Acknowledgment prove the task was completed correctly?

No. It describes the user reply in the supplied exchange. Correctness of the underlying work requires separate evidence.

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 stop reply reaction input

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