Description:

The Detect Language (Google) step enables a FlowWright workflow to automatically determine the language of supplied text by using Google's language detection service.

Many business workflows receive content from users, customers, suppliers, or external systems in multiple languages. Before translating, routing, or processing this content, workflows often need to determine which language has been submitted. This step analyzes the supplied text and returns the detected language together with optional reliability and confidence information.

The detected values can then be used to make workflow decisions, select translation services, route work items to regional teams, generate multilingual notifications, or support downstream AI and document-processing activities.

Typical uses include:

• Detecting customer message languages
• Routing requests to regional support teams
• Selecting the appropriate translation workflow
• Localizing workflow notifications
• Processing multilingual forms
• Identifying document languages
• Supporting AI-powered multilingual workflows
• Automating international business processes

This step allows workflows to intelligently process multilingual content without requiring users to explicitly specify the language.

Usage:

The Detect Language (Google) step is typically used before translation, workflow routing, document processing, or AI analysis.

During execution:

1. Read the input text.
2. Submit the text to the Google language detection service.
3. Detect the language of the supplied content.
4. Store the detected language in the configured workflow variable or global variable.
5. Optionally store the returned reliability and confidence values.
6. Continue workflow execution through either the True or False return path.

A typical workflow might look like this:

Typical workflow scenarios include:

• Detecting languages before translation
• Routing multilingual customer requests
• Selecting regional workflow paths
• Processing multilingual forms
• Preparing AI prompts using the detected language
• Categorizing multilingual documents
• Supporting international customer service
• Automating multilingual document workflows

Example:

Let’s build and execute the “GoogleDetectLanguageDef” example.          

• Create a new process definition called “GoogleDetectLanguageDef” and open the definition in designer mode. 
• Drag a “GoogleDetectLanguage” step to the canvas. 
• Connect the dots between the “Start” step and “GoogleDetectLanguage” steps, as shown above. 
• Define a few variables or globals to store the language-check result, reliability, and confidence-level values.
• Click the “GoogleDetectLanguage” step to configure its “Required” properties. Provide a name for the step. Enter the non-English text to detect. Specify a variable or global reference to store the language result. Click the Save button. Note: Click the "AI Predict" button to have Copilot add new process steps that match your process description. 
   

• Click the “GoogleDetectLanguage” step to configure its “Optional” properties. Provide a variable or global reference to store the reliability and confidence level values. Click the Save button. 

• Save the process definition, create a process instance, and execute it. The Step should detect the language of the provided text at runtime. Render the process instance and verify the step properties.

Tips:

• Execute this step before translation when the source language is unknown.
• Store the detected language in a reusable workflow variable for downstream workflow activities.
• Capture the reliability and confidence values when workflows require additional validation before translation or routing.
• Route the False execution path to logging and notification activities for easier troubleshooting.
• Use the detected language to dynamically select localized email templates, forms, or business rules.
• Combine this step with Translate Text (Google Translate), Translate Text (Azure ML Language Translator), Ask AI, Send Email, REST Call, or document-processing steps to build intelligent multilingual workflows.

Notes:

• The step accepts multiline text input.
• The detected language is stored in the configured workflow variable or global variable.
• Reliability and confidence outputs are optional.
• The input text is not modified.
• Both the True and False return paths should be implemented for complete workflow handling.
• Ensure that the Google Cloud language detection integration is configured before executing this step.
• Language detection details are recorded in the FlowWright workflow execution log.

Detect Language (Google) vs. Translate Text (Google Translate):

Although both steps integrate with Google Cloud language services, they perform different functions.

As a general guideline:

• Use Detect Language (Google) when the language of incoming text is unknown and workflow decisions depend on identifying it.
• Use Translate Text (Google Translate) when the source content needs to be translated into another language for communication, reporting, or downstream processing.

Definition Sample:

You may download the sample workflow definition from the link provided and import it into your FlowWright environment.

Note: Verify and complete any missing configuration after importing the sample, including:

• Input text
• Variable or global variable for the detected language
• Optional variables for reliability and confidence
• Success and failure workflow branches
• Google Cloud language detection service configuration and credentials

After verifying the configuration, save and publish the workflow before execution.

Click here to download the sample file.