Jev anchor promise check

Check whether link text describes its destination

Give an anchor phrase and the destination's content. Compare a clear description with a generic label or a promise the page does not fulfill.

Make the link phrase describe what the reader gets.Live API
Try an example

Original synthetic input. Edit the task or evidence to make a new API request.

Source: Workflow inspiration on X

Source and example scope

The inputs, rubric and preview are original. This window demonstrates the stated decision only; it does not reproduce the source application or its measurements.

Review the anchor phrase against the supplied destination description.

Decision rules and labels
Accurate descriptionUnsupported promiseToo genericNeed destination
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

How does Jev anchor promise check use its evidence?

Jev anchor promise check checks whether the words of a link set an accurate expectation for its supplied destination.

The source describes Jev-assisted internal-link analysis including anchor suggestions. This page implements an original anchor-review step instead of choosing a destination or placement. It crawls no site and adopts none of the source's costs, speed or business outcomes.

Google's link guidance recommends descriptive, concise text relevant to both source and destination. Our fictional cases focus on the destination promise: a guide should not be labeled as an interactive tool or guaranteed service. The model returns a local review report and changes no link.

Original Jev anchor promise check workflow diagram showing supplied evidence, a typed decision and the local preview.
Original workflow illustration. The output is a local preview, not an executed action or source screenshot.
How it works

Try the example in four steps

Use the sample to understand the rule, then test your own input for link text review.

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

    Add the information to check

    Give an anchor phrase and the destination's content.

  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 Accurate description, Unsupported promise, Too generic, Need destination. 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 destination before using a result. The label is a decision about the supplied information, not an executed action.

Our API test

What the six original inputs returned.

What the six original inputs returned.
Original test inputObserved labelLeading probability
An accurate guide labelAccurate description97%
A tool promise for an articleUnsupported promise100%
An unexplained link phraseToo generic99%
Unknown destination contentNeed destination95%
A supplied downloadable fileAccurate description100%
An unsupported outcome guaranteeUnsupported promise100%
  • Measured adapter round trips: 567-2350 ms. Estimated input cost: $0.00002121-$0.00002159 per request. These observations are not a latency guarantee or invoice.

6 actual Jev API calls on October 1, 2026. Original synthetic inputs check this rubric and handoff; they do not establish held-out accuracy. Probabilities are model outputs.Verified

Understand the results

Source and example scope

The maintenance-guide fixture names the informational destination accurately. Accurate description concerns the supplied capability, not SEO ranking potential. A real editor should also read the surrounding source sentence and verify the actual target before applying the phrase.

Source and example scope

The tool fixture promises an interactive diagnosis feature that the supplied destination lacks. Unsupported promise preserves that mismatch even though the topic is related. Topic relevance alone cannot establish that a reader will receive the promised type of resource.

Source and example scope

The click-here fixture has a known destination but no descriptive link wording. Too generic records that wording gap. The demo does not generate a replacement phrase; a separate author can choose one and run a new request against the verified destination.

The unknown-destination fixture makes a download promise without a target description

The unknown-destination fixture makes a download promise without a target description. Need destination preserves the missing evidence. A filename-looking URL or a page title should not be treated as proof that a downloadable checklist exists.

The downloadable-checklist fixture explicitly supplies the promised file capability

The downloadable-checklist fixture explicitly supplies the promised file capability. Accurate description reviews that evidence. This demo does not request a file or validate its format; a publication process still needs to check that the real download opens and matches its description.

The repair-guarantee fixture extends an informational guide into a promised service and outcome

The repair-guarantee fixture extends an informational guide into a promised service and outcome.

Read the example notes

Unsupported promise records that scope difference. These six original phrases are a wording exercise, not a link-growth or ranking benchmark. The output stays local and keeps target selection, placement and HTML validation separate.

Using the result in your application

Download the exact sample requests and saved observations below.

Read the example notes

Expected labels are original fixture checks and stay outside the request sent to Jev. The observation file preserves the complete probabilities and the hash of each exact request. Editing a task, rubric or candidate requires a fresh response; a matching sample name does not make an older answer current.

Using the result in your application

The JavaScript runner makes one independent SDK request for a chosen sample ID.

Read the example notes

It reads TYPESAFE_API_KEY privately from the environment and has no automatic retry. The Python consumer operates offline: it checks the rubric, labels, unique sample identities, request hashes and valid probability distributions before selecting a fixed local preview. A tied leading result remains pending for review.

Source and example scope

The page reports measured adapter round trips and estimated input cost for the recorded calls.

Read the example notes

Those values describe these requests, not a provider latency guarantee or a billing statement. Six deliberately authored fixtures can check the stated behavior, but they do not establish accuracy on an unseen dataset. Keep disagreements and missing-input examples when testing an integration.

Runnable offline example

Replay one request and inspect the saved preview.

View the code example
Replay commands
npm install @typesafe-ai/sdk@0.6.0
# Set TYPESAFE_API_KEY privately in your shell.
node run-choice-sample.mjs samples.json guide
python preview_choice_workflow_v2.py samples.json saved-api-results.json
Scope of this demo

Where does this decision fit?

Useful with explicit supplied evidence

  • Review whether a supplied link phrase accurately describes a destination capability and is descriptive enough for a reader. Original fictional pages and phrases; no link placement, destination selection, crawling or ranking claim.
  • Inspecting the original task and a fixed output before integrating external tools.
  • Comparing an explicit expected label with the complete recorded distribution.

Needs separate implementation or evidence

  • Inferring facts absent from the supplied input.
  • Treating a semantic selection as authorization to act.
  • Executing an external action or generalizing six fixtures into an accuracy claim.
Example FAQ

Questions about this original decision workflow.

Keep relevance, compliance and execution separate.

What does anchor promise checking review?

It reviews the supplied link phrase against the destination's stated capability.

Does the tool choose a destination?

No. The destination is already supplied; this is an anchor wording review.

Can a related guide be described as a tool?

Only if the supplied destination actually offers that tool. Related topic alone is insufficient.

Does Accurate description improve rankings?

This label makes no ranking claim. It checks the expectation set by the wording.

Will the report rewrite a live link?

No. It emits a fixed local report without modifying HTML.

Try a task from your own workflow

Change the supplied task or evidence here, then inspect the live response. Playground supports another explicit decision.