Jev agent event delivery timing

Decide when an event matters to an agent's current work

Describe an event, the agent's goal and its current action. Compare an interruption candidate with news that can wait until the next step or has no effect.

When would the agent need this external event?Live API
Try an example

Continuing would use an invalidated patch base.

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.

Compare the external event with the goal and current action.

Decision rules and labels
Interrupt candidateNext-step candidateNo effectNeed event
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

Two relevant events can matter at different points in the same task.

A changed patch base affects the action about to run, so the first preset expects Interrupt candidate. A completed comparison export can wait while the agent reads an unchanged old fixture. Both events relate to the goal, but only one invalidates the current step.

An urgent label in a separate marketing feed does not create a dependency on the active project. Conversely, conflicting records about a changed input file leave the impact unresolved. The rule requires the goal, current action and event together.

The pinned notification decision compares an event with ongoing work to choose a delivery point. These original scenarios return a candidate label only. The window does not interrupt an agent, post a notification or independently verify the reported impact.

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 agent event timing.

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

    Add the information to check

    Describe an event, the agent's goal and its current action.

  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 Interrupt candidate, Next-step candidate, No effect, Need event. 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 event 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
Patch base changedInterrupt candidate99.0%
Background result can waitNext-step candidate100%
Other workspaceNo effect100%
Urgent wording aloneNo effect100%
Conflicting impact recordsNeed event60.0%
Current action absentNeed event33.0%

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

  • Reviewing external events against current work
  • Separating immediate impact from next-step relevance
  • Identifying irrelevant or conflicting event reports

Outside this demonstration

  • Interrupting an active agent
  • Inferring priority from urgent wording
  • Verifying a file change or external event
Example FAQ

Questions about agent event delivery timing.

Input scope and downstream handling determine what this judgment means.

Is this the same as checking whether an event is relevant?

No. A relevant result may be needed after the current step rather than during it. The current action determines that additional timing distinction.

Does Interrupt candidate stop anything?

No. It is the highest-probability label for the supplied impact. Any actual interruption policy belongs in a separately tested application.

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 agent event delivery timing input

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