Jev agent work phase

Identify an agent's current work phase

Provide the latest activity and ordered steps. Distinguish reading, planning, editing and running checks from waiting or being stuck, without assuming the work is complete.

Which phase describes the current activity?Live API
Try an example

The current activity gathers context.

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.

First choose Need activity for missing, conflicting, equally current or unlisted activity.

Decision rules and labels
Read contextPlan approachEdit filesRun checksOther phaseNeed activity
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 failed test can be followed by an edit. The latest activity decides the phase.

The failed-check preset ends with a saved code edit, so its expected phase is Edit files. The validation preset instead says the regression suite is running now. Neither observation establishes that the fix works.

Explicit waiting, wrapping up or being stuck takes the Other phase label in this demonstration. This grouping keeps the decision small; it is not the full phase table used by the linked project. Equally current conflicting activity records need clarification.

The pinned board.read source asks what an agent is doing from its recent steps and latest message. These original presets exercise a narrower six-label rule. The window does not monitor a live agent, update its board or certify task completion.

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 activity phase.

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

    Add the information to check

    Provide the latest activity and ordered steps.

  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 Read context, Plan approach, Edit files, Run checks, Other phase. 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 activity 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
Read the callerRead context99.0%
Choose the approachPlan approach97.0%
Fix after a failed checkEdit files100%
Run validationRun checks88.0%
Explicitly stuckOther phase98.0%
No current activityNeed activity99.0%

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

  • Reading a supplied activity trace
  • Separating current work from earlier failed checks
  • Spotting missing or conflicting activity evidence

Outside this demonstration

  • Monitoring an agent automatically
  • Determining whether a task is complete
  • Replacing the linked project’s full phase table
Example FAQ

Questions about agent work phase.

Input scope and downstream handling determine what this judgment means.

Why combine waiting, wrapping up and stuck?

This demonstration groups those explicit states under Other phase. A production status board can keep them separate, but it would need its own outcome definitions and tests.

Does Run checks mean the checks passed?

No. It describes the current activity. A result and its scope are needed before reporting that any check passed.

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 work phase input

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