To access workflow step settings, select Configuration > Settings > Workflow > Workflow steps.
Workflow steps are displayed in a table containing the following details:
Step name.
Description.
Step type.
Created by.
Workflow use – this column displays the number of workflow definitions in which a step has been used.
Active – this column displays one of the two icons:
the information icon
in the last table column – when you hover over it, the ID of the relevant step will be displayed.
To create a new workflow step, select the Add button. Then, in the Create workflow step popup, select the relevant values for the workflow step settings.
To edit an existing workflow step, select it from the table. Then, in the Edit workflow step popup, select the relevant values for the workflow step settings.
Table 47. Workflow steps settings
Setting | Description | Mandatory/Optional | Type | Valid values |
|---|
Type | Select one of the standard or additional workflow steps. | Mandatory | Dropdown | Valid Standard steps values are: Translate – users can enter and edit translations and add comments. Correct – users can edit translations and enter comments. Review – users can only enter comments about translations; they cannot edit the translations. LQA (Linguistic Quality Assessment) – users can check translation errors.
Valid Additional steps values are: Management tasks – files can be downloaded, but cannot be updated. Example 16. Usage of the Management task step It can be an approval step before the translation process starts. Others include: entering cost details, approving costs and proposals, printing files, sending files to the client, etc.
Non CAT tool process – files can be downloaded and updated in XTM Cloud , but the translation memory (TM) and project segments will not be modified. Example 17. Usage of the Non CAT tool process step DTP step after translation, in which some layout changes are required. Changes to the target text made in this type of step are not saved in the TM or terminology database.
Automatic – enables you to perform one or more of these actions (which are described in detail below): Use AI Post-Edit. For details, see Global AI Post-Edit settings. Save and approve the TM for selected segments. Set segments to Completed status. Update XLIFF:doc status. NoteThis option is only available if TIPP is activated in Configuration > Settings.
|
Name | Enter a unique name for the workflow step. | Mandatory | Text field | Empty (default) Enter the workflow step name using Latin letters, digits and/or the following characters: - _ , . ^ ! @ # $ % & ( ) |
Description | When you select a step type, the Description setting is automatically filled with its definition. However, you can customize this description. | Automatic | Text field | Filled automatically depending on the selection that you have made for the Type setting. You can customize the description using alphanumeric values. |
Active | Specify if the workflow step should be active and available for selection when you or another user with the XTM Cloud Administrator role create a workflow definition and for Project Managers in the Workflow Editor (for details, see Project Editor: Workflow) or in Beta Workflow Editor (for details, see Project Editor – Beta Workflow Editor). | Optional | Checkbox | Valid values: |
Enables you to perform these actions (in the order shown): | This parameter is available when the Automatic option is selected within the Additional steps workflow type. | Mandatory | Checkboxes | Valid values: Use AI Post-Edit – select this checkbox to activate the AI Post-Edit feature for your automatic step (for details, see Global AI Post-Edit settings). When you do so, these additional settings are displayed: Select LLM engine dropdown. Currently, this setting is inactive, and its value is set to OpenAI GPT. This means that, currently, only OpenAI GPT can be used for the AI Post-Edit feature. Check terminology (recognized for the segment) checkbox. When you select this setting, the AI Post-Edit feature will ensure that terminology is used consistently in the target segments. ImportantTo grant the AI Post-Edit feature access to your terminology, ensure that you select the Match terms in analysis setting in the global terminology settings. For details, see Terminology engines. Alternatively, Project Managers can enable this setting at customer level (for details, see Customer Editor – Settings). Basic QA check checkbox. When you select this setting, the AI Post-Edit feature will ensure that the translation is consistent with the source text in terms of its: content. It ensures that URLs, variables, email addresses, and special characters have been included in the translation. formatting. It ensures that indentation, newline, and bracket pairs match the source text. quality. It automatically performs spelling and grammar checks on target segments.
in the Parameters section, these settings are displayed: Formality checkbox. When you select this setting, you will be able to select one of the three formality levels: Gender neutrality checkbox. When you select this setting, the AI Post-Edit feature will ensure that the translation is gender-neutral. Follow locale conventions checkbox. When you select this setting, the AI Post-Edit feature will ensure that the translation adheres to the locale-specific rules and formatting requirements for data elements such as numbers, time and dates, measurement, addresses and phone numbers, currencies, etc. For more details, see "Locale conventions" in MQM (Multidimensional Quality Metrics).
ImportantAt least one of these automatic step settings must be made, for the AI Post-Edit feature to work: For details, see descriptions of these settings in the list above.
Business use caseThe AI Post-Edit feature helps you reduce post-editing time and cost while ensuring that the final output meets your required quality standards. A key benefit is its flexibility: an automatic workflow step enables Project Managers to use Large Language Models (LLMs) to enhance various outputs, including human translation (HT), machine translation (MT), and LLM-generated translation. It can be used in either fully automated (LLM-only) or hybrid workflows (HT/MT + LLM). The AI Post-Edit feature leverages XTM Cloud’s resources. It sends the Translation Memory (TM) for reference and has access to your terminology. Because of this, it can adjust the content's tone and voice automatically, while ensuring that the high-quality output adheres to company terminology and brand voice. NoteIf required, changes made to the target segment by the AI Post-Edit feature can be reverted. To do so, users with the Project Manager role should use the workflow rollback feature. For details, see Rollback to a previous step in the workflow. Save and approve the TM for selected segments – this option enables automatic approval of segments which meet any of the selected criteria. XTM Cloud can automatically approve segments with: Changed target text. Select it to automatically approve segments in which the target text is different from the source text. Completed status. Select it to automatically approve segments in which the the status has been set to “Completed” in the preceding step. To be corrected status. Select it to automatically approve segments with “To be corrected” status. Match type. Select it to automatically approve segments with one of the following match types available in the dropdown list: ICE. Leveraged. Non-translatable.
XLIFF:doc status. Select it to automatically approve segments with one of the following specific XLIFF:doc statuses available in the dropdown list: New. Translated. Proofed. Validated.
NoteThis option is only available if TIPP is activated in Configuration > Settings.
Set segments to Completed status checkbox. When you select this setting, all segments will be set to 'Completed'. If you have selected the Use AI Post-Edit checkbox, these radio buttons are displayed: For all segments. When you select it, all segments will be set to 'Completed' even if the AI Post-Edit failed for that step (for example, because of the problems with the LLM connection). Only for segments for which AI Post-Edit has been performed. When you select it, only segments that have been processed successfully by the AI Post-Edit feature will be set to 'Completed' .
Update XLIFF:doc status checkbox. When you select this setting, these radio buttons are displayed: NoteThis option is only available if TIPP is activated in Configuration > Settings. all XLIFF:doc statuses radio button. When you select it, all XLIFF:doc statuses will be updated to the one selected from the dropdown: New. Translated. Proofed. Validated.
You can additionally set that a segment can only be updated if it meets one or more of the following conditions: XTM status is done (“Completed”). TM match type is one or more of the following: ICE. Leveraged. Non-translatable.
XLIFF:doc status is one or more of the following:
minimum XLIFF:doc status radio button. When you select it, the minimum XLIFF:doc status in your project will automatically be changed to the one selected in the dropdown: New. Translated. Proofed. Validated.
You can additionally select the Set segments to Completed status setting – the XTM Cloud status will be changed to “Completed”.
|
If action fails then | This setting is available when you have selected the Automatic option for the Additional steps workflow type. Specify what should happen if the automatic workflow step fails. | Mandatory | Dropdown | Valid values: move to the next step. stay in the same step.
|