Jev architecture review trigger

Check whether a code change needs architecture discussion

Describe the proposed boundary change and relevant design agreement. Distinguish local implementation from an unresolved architectural decision or a covered design.

What does the supplied design context support?Live API
Try an example

The new shared lifecycle owner lacks a supplied agreement.

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 change.

Decision rules and labels
Discussion neededExisting design appliesLocal implementationNeed design context
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 design document helps only when it covers the changed boundary.

The queue preset includes an approved agreement that covers the interface and retry owner. The direct-write preset contradicts the supplied agreement, so the existence of a document does not remove the need for discussion.

A local helper extraction is different from transferring connection ownership to a shared pool. The rubric asks about boundaries, contracts and lifecycle ownership rather than the number of files changed.

The result is a discussion trigger for the evidence provided. It does not verify an ADR, decide whether an architecture is good or authorize a merge. A real reviewer must inspect the actual design and patch.

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 checking a code change and reviewing a flagged line
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 architecture discussion check.

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

    Add the information to check

    Describe the proposed boundary change and relevant design agreement.

  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 Discussion needed, Existing design applies, Local implementation, Need design context. 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 Discussion needed, Need design context 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
New shared ownerDiscussion needed90.0%
Agreed queue interfaceExisting design applies60.0%
Private refactorLocal implementation100%
Design contradictedDiscussion needed95.0%
Unknown agreementNeed design context67.0%
Unrelated design documentDiscussion needed86.0%

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

  • Triage before an architecture review meeting
  • Checking a patch against a relevant agreed design
  • Identifying missing design-status context

Outside this demonstration

  • Approving a system architecture
  • Authenticating an approval record
  • Treating any design document as relevant
Example FAQ

Questions about architecture review trigger.

Input scope and downstream handling determine what this judgment means.

Does every refactor require design discussion?

No. The local preset establishes unchanged boundaries and behavior. The decision follows the supplied impact, not the word refactor.

Why distinguish missing design status from no agreement?

An unknown status lacks evidence. An explicit statement that no agreement covers a new shared boundary supports a discussion trigger under this rule.

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 architecture review trigger input

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