Summary
Purpose
The wxrks editor can now run an AI quality review on top of the standard QA checks. This review looks at each source→target segment, flags likely quality problems ("Smells"), and turns them into a Confidence Score so you can see, at a glance, how trustworthy each translation is.
Use this feature to prioritize review effort: focus on low-confidence segments first, understand why a segment was flagged, and hide the flags you decide are not relevant.
Key Concepts
Term | Meaning |
Smell | A potential quality problem that the AI review detected in a segment (for example a mistranslation, awkward wording, or terminology issue). Each Smell has a category, a severity, and a short explanation. |
Severity | How serious a Smell is: Blocker, Critical, Major, Minor, or Info. |
Confidence Score | A 0–100% value showing how confident wxrks is in a segment's quality. A segment with no Smells is 100%. When a segment has Smells, its score reflects the most severe one. |
Overall Confidence | The combined confidence for the whole work unit, shown at the top of the QA panel. |
Issues vs. Smells | Issues are the traditional rule-based QA warnings (tags, numbers, length, spelling, and so on). Smells are the new AI-detected findings. Both appear in the QA panel. |
How severity maps to confidence
The Confidence Score of a segment is driven by its most severe Smell:
Severity | Segment confidence |
No Smells | 100% |
Info | 100% |
Minor | 80% |
Major | 50% |
Critical | 30% |
Blocker | 0% |
Confidence is color-coded wherever it appears:
Green — High (80% and above)
Orange — Medium (50%–79%)
Red — Low (below 50%)
Turning On the AI Review
The AI review runs as part of QA, but only when you enable it.
Open the QA panel in the editor.
Click Filters to open QA Settings.
In the Execution section, turn on Enable Smells.
Click Apply.
Running QA
Start QA with Run QA (or Run for Current / Run for All when work units are joined).
QA runs in two phases:
Checks — the standard rule-based QA.
Smells — the AI review, shown with a progress bar counting how many segments have been analyzed.
When the run finishes, Confidence Scores and Smells appear automatically. You do not need to reload the editor.
The date and time of the last run are shown as "The report was run on…" above the results.
Reading the Confidence Score
On each segment in the editor
Each segment shows a small shield icon with its confidence percentage (for example, 92%). Hover over it to confirm it is the QA Confidence Score. The color follows the High / Medium / Low scale above.
This badge appears both in the translation view and in the review view.
Showing or hiding the segment badge
Open the editor Settings panel.
Under your preferences, use Show Confidence Score to turn the per-segment badge on or off.
This setting is saved to your preferences, so it is remembered the next time you open the editor.
Overall Confidence for the work unit
At the top of the QA panel, Overall Confidence summarizes the whole work unit. It uses the same color scale, so a red or orange overall score is a quick signal that the work unit needs attention.
Working With Smells in the QA Panel
Smells appear in the QA results next to the traditional Issues. Each Smell shows:
Its category (for example, a terminology or accuracy label).
A severity pill (Blocker, Critical, Major, Minor, or Info).
A short explanation of the problem.
Ignore a single Smell
Click the eye icon on a Smell to ignore it. Ignored Smells no longer count against the segment. Click the icon again (now an open eye) to bring it back.
Ignore an entire category
From a Smell's three-dots menu, choose Ignore all of this category, or
Use the eye-slash action on a category chip at the top of the results list.
To bring a category back, use the eye action on the same chip.
Filter what you see
Category chips — click a chip to show only that category's Smells. Use the arrow at the end of the chip row to load more categories when there are many.
Segments with Issue / Segments without Issue — narrow the list to segments that do or do not have findings.
Show ignored issues — reveal items you previously ignored so you can review or restore them.
Clear — reset the active filters.
Filter Smells by confidence
Next to Overall Confidence, click Smells to open the Confidence filter. Drag Show confidence up to to show only Smells at or below a chosen confidence level (for example, ≤ 50% to focus on the most serious findings). A dot on the button indicates the filter is active. Use Clear filter to remove it.
Choosing How Issues and Smells Are Displayed
The QA Issues View setting (in the editor Settings panel) controls the layout:
Grouped — Issues and Smells are listed together on each segment.
Split — the QA panel adds Issues and Smells tabs so you can review each type separately.
This preference is saved to your account.
Filtering Segments by Confidence
You can also filter the segment list itself (not just the QA panel) by confidence.
Open the Filter panel in the editor.
Turn on Confidence Score to filter by score, then choose a comparison: - Any score, Equal to, Greater than, Greater equal than, Less than, or Less equal than. - For any comparison other than Any score, enter a value from 0 to 100.
Or turn on No Smells to show only segments with no Smells at all.
These filters help you jump straight to the segments that need work — for example, "confidence less than 50".
Downloading the QA Report
Use Download Report to export the QA results as a spreadsheet. When the AI review has run, the report includes the Smell findings alongside the standard QA Issues.
Important Behavior and Edge Cases
Smells only appear when enabled. If you did not turn on Enable Smells before running QA, you will see standard Issues but no Smells or Confidence Scores.
Confidence reflects the worst finding. A single Blocker drops a segment to 0%, even if everything else looks fine. Read the explanation before acting.
Ignoring is shared and reversible. Ignoring a Smell or category hides it for the work unit but never deletes it — turn on Show ignored issues to restore anything.
The badge is a display preference. Turning off Show Confidence Score only hides the per-segment badge; it does not change scores, Smells, or the QA report.
Editing a segment can change its score. After you fix and re-run QA, confidence and Smells refresh to reflect the new translation.
Troubleshooting
I ran QA but see no Confidence Scores or Smells. Confirm that Enable Smells was on in QA Settings before the run, then run QA again.
The confidence badge is missing on segments. Check that Show Confidence Score is on in the editor Settings panel, and that the AI review has finished running.
A segment shows a very low score but the translation looks correct. Open the Smell's explanation. If you disagree, ignore that Smell (or its category). The score updates to reflect the remaining findings.
A category is cluttering my results. Use Ignore all of this category from the Smell menu or the category chip. Restore it later with the chip's eye action.
I hid something by mistake. Turn on Show ignored issues, find the item, and click its eye icon to enable it again.
Quick Reference
I want to… | Where |
Turn on the AI review | QA Settings → Execution → Enable Smells |
Run the review | QA panel → Run QA (or Run for Current / Run for All) |
See a segment's confidence | Shield badge on the segment (requires Show Confidence Score) |
See the work unit's confidence | Overall Confidence at the top of the QA panel |
Switch grouped/split layout | Editor Settings → QA Issues View |
Ignore one Smell | Eye icon on the Smell |
Ignore a whole category | Smell menu → Ignore all of this category, or category chip |
Show only serious Smells | Smells confidence filter → Show confidence up to |
Filter segments by score | Filter panel → Confidence Score |
Show only clean segments | Filter panel → No Smells |
Restore hidden items | Show ignored issues toggle |
Export results | QA panel → Download Report |