Back to top image

Smartling's AI Toolkit Dashboard

 

The AI Toolkit Dashboard gives you a centralized view of how your organization uses Smartling's AI Toolkit. Use it to monitor subscription budgets, track word usage across capacity bundles, and measure how AI-powered features optimize your translation workflows.

Accessing the AI Toolkit Dashboard

To open the AI Toolkit Dashboard:

  • From the top navigation of your Smartling dashboard, click AI Hub.
  • Click AI Toolkit Dashboard.

Tip: To enable Smartling's AI Toolkit or to learn more, please reach out to your Smartling Customer Success Manager.

Word Usage

The Word Usage widgets help you track consumption against your Smartling capacity bundles.

In addition to your Smartling platform subscription, you can purchase a pre-defined number of MT words and/or AI Toolkit words. These capacity bundles track how much content gets translated in your Smartling account — either with Machine and LLM Translation, or with AI Toolkit features. Packages can be purchased separately based on your translation needs and remain valid for the duration of your platform subscription.

Each Word Usage widget shows how much capacity has been consumed for its respective bundle, displaying both the percentage and the actual number of words used.

Info: A warning is displayed once the word usage capacity for your account is running low or has been reached. We recommend reaching out to your Customer Success Manager to discuss your options to keep translating content in Smartling.

Tip: Paid-off overages may still be included in the usage numbers displayed on this page. Any discrepancies will be addressed in a future update. If you require clarification, please reach out to your Customer Success Manager.

MT Words Used

This widget shows the number of words translated with an MT provider, including words processed through:

The following do not count towards your MT words capacity:

  • MT suggestions displayed in the CAT Tool
  • Strings using TM Match Insertion
  • Translations using Smartling's AI-Powered Human Translation (AIHT) workflow

AI Toolkit Words Used

This widget shows the number of words that went through a translation step where at least one AI Toolkit feature is enabled.

Translations using Smartling's AI-Powered Human Translation (AIHT) workflow or other workflows managed by Smartling Language Services are not counted towards your AI Toolkit usage.

AI Subscription

The AI Subscription widget provides an at-a-glance overview of your AI Subscription budget.

At the top of the widget, a status badge indicates the current health of your subscription (for example, Healthy). A progress bar displays the percentage of your total budget spent, giving you a quick visual indicator of your remaining capacity.

Usage Breakdown

Below the progress bar, the Usage Breakdown chart tracks your AI Subscription consumption over time. By default, usage is displayed in words. To view usage by cost, use the View by toggle in the top-right corner of the chart.

Click "View report" to open the AI Subscription Usage report for a detailed breakdown of your subscription consumption.

AI Toolkit Dashboard Reports

The AI Toolkit Dashboard provides pre-configured reports that show how Smartling's AI Toolkit optimizes your machine and LLM translation process.

All reports can be filtered by date range, language pair, and workflows.

Info: Report data is refreshed 24 hours after translations have been submitted from a Post-Edit, Edit, or Review step.

Translation Memory Leverage Reports

Smartling allows you to enable TM Match Insertion for Machine Translation, which substitutes translation memory entries for machine translations when a match above a specified threshold is available. Combined with AI Adaptive Translation Memory, these features can significantly increase TM leverage in machine translation workflows.

The TM Leverage reports display the number of words from your translation memory that were leveraged across all MTPE workflows (workflows using machine translation followed by a human Post-Edit, Edit, or Review step).

To qualify as "discounted leverage" in these reports, the fuzzy match percentage must reach at least the first discount tier defined in your Fuzzy Match Settings. For example, with Smartling's default Fuzzy Match Profile, only matches of at least 85% are considered leverage.

Workflows with AI features enabled in the translation step but without a human Post-Edit, Edit, or Review step are not included in TM Leverage reports. Words in these workflows do not count towards discounted leverage, as discounted leverage only applies when a human is involved in a Post-Edit, Edit, or Review step and the fuzzy match profile is applied to that step.

1. TM Leverage in MTPE Workflows

This report shows the percentage of words going through an MTPE workflow within the last 30 days that benefitted from:

  • Discounted leverage without AI Adaptive Translation Memory
  • Discounted leverage gained by AI Adaptive Translation Memory
  • SmartMatch
    TM Leverage in MTPE Workflows - circle graph showing discounted leverage, AI Adaptive TM leverage, and SmartMatch

The white, unlabeled portion of the circle graph represents words that were machine translated without TM leverage.

2. AI Adaptive Translation Memory Performance

This report compares translation memory leverage without AI Adaptive Translation Memory to the additional leverage gained by enabling AI Adaptive Translation Memory, based on content processed through MTPE workflows within the last 30 days.

3. Translation Memory Leverage in MTPE Workflows Over Time

This report shows a month-by-month breakdown of how many words in MTPE workflows benefitted from discounted translation memory leverage. Hover over the timeline to see the percentage of translated content leveraged through:

  • Discounted leverage without AI Adaptive Translation Memory
  • Discounted leverage gained by AI Adaptive Translation Memory
  • SmartMatch

Click "View settings" to access your MT Profiles, where you can enable TM Match Insertion in Machine Translations.
Click "View report" to open the full report, which can be downloaded in CSV format.

Tip: To achieve cost savings on the Post-Edit step based on fuzzy matches, ensure your Fuzzy Match Settings are also applied to the post-translation step.

Language Quality Estimation (LQE) Reports

The Language Quality Estimation (LQE) Agent uses AI to predict the quality of each machine-translated string, helping you understand how much human editing may be needed before a translation can be published.

1. Language Quality Estimation Levels

This report displays the Language Quality Estimation level for all machine-translated words processed by the LQE feature within the last 30 days. Hover over the graphic to see both the percentage and word count for each level.

2. Language Quality Estimation & Human Edit Rate

This report shows the total number of machine-translated words processed by the LQE feature within the last 30 days, with a breakdown by quality estimation level (word count and percentage).

The report also includes two key editing metrics:

  • Average Edit Rate — The mean number of edits per translated string, calculated by dividing total edits by total translated strings.
  • Median Edit Rate — The midpoint edit rate across all strings, normalized for string length. This provides a more robust measure of typical editing effort, as it prevents extremely long or short strings from skewing the result.

Click "View settings" to learn how Language Quality Estimation can be enabled for your MTPE workflows.
Click "View report" to open the full report, which can be downloaded in CSV format.

Table of Contents