Removed deprecated services

Author: GraemeMalcolm

learn-pr/wwl-data-ai/analyze-text-ai-language/includes/2-provision-resource.md

@@ -6,6 +6,9 @@ Azure Language in Foundry Tools is designed to help you extract information from
 
     :::image type="content" source="../media/text-analytics-resource.png" alt-text="Diagram showing an Azure Language resource performing language detection, named entity recognition, and PII extraction.":::
 
+> [!NOTE]
+> Azure Language also provides functionality for sentiment analysis, summarization, key phrase extraction, and other common language-related tasks. These deprecated capabilities are provided to support existing applications.
+
 ## Using a Microsoft Foundry resource for text analysis
 
 To use Azure Language in Foundry Tools to analyze text, you must provision a Microsoft Foundry resource in your Azure subscription.

learn-pr/wwl-data-ai/develop-text-analysis-agent-language-mcp/includes/01-introduction.md

@@ -1,8 +1,8 @@
-Azure Language in Foundry Tools provides a set of natural language processing (NLP) capabilities that you can use to analyze text. These capabilities include sentiment analysis, named entity recognition, key phrase extraction, summarization, and more.
+Azure Language in Foundry Tools provides a set of natural language processing (NLP) capabilities that you can use to analyze text. These capabilities include language detection, named entity recognition, and personally identifiable information (PII) extraction.
 
 While you can call these capabilities individually through REST APIs or SDKs, you can also make them available to an AI agent through the **Azure Language Model Context Protocol (MCP) server**. This approach lets the agent dynamically select and call the appropriate language tool based on a user's request, without you needing to write specific code for each capability.
 
-For example, suppose you work for a company that needs to analyze customer feedback. Customers submit reviews in multiple languages, and your team needs to understand the overall sentiment, identify the people and places mentioned, and generate summaries of the feedback. Rather than building separate integrations for each of these tasks, you can create an AI agent that uses the Azure Language MCP server to perform all of them through a single tool connection.
+For example, suppose you work for a company that needs to analyze customer feedback. Customers submit reviews in multiple languages, and your team needs to determine which language was used, identify the people and places mentioned, and redact any personal details in the reviews. Rather than building separate integrations for each of these tasks, you can create an AI agent that uses the Azure Language MCP server to perform all of them through a single tool connection.
 
 In this module, you learn how the Azure Language MCP server works, how to connect it to an AI agent in Microsoft Foundry, and how to build a client application that interacts with the agent programmatically.
 

learn-pr/wwl-data-ai/develop-text-analysis-agent-language-mcp/includes/02-understand-language-mcp.md

@@ -21,17 +21,15 @@ The Azure Language MCP server exposes Azure Language NLP capabilities as tools t
 
 | Capability | Description |
 |---|---|
-| **Named Entity Recognition** | Identifies and categorizes entities in text, such as people, places, organizations, dates, and quantities. |
-| **Sentiment Analysis** | Determines whether text expresses positive, negative, or neutral sentiment, and can extract opinions about specific aspects. |
-| **Summarization** | Generates concise summaries of longer text content. |
-| **Key Phrase Extraction** | Identifies the main concepts and key phrases in text. |
-| **PII Redaction** | Detects and redacts personally identifiable information such as names, addresses, and phone numbers. |
 | **Language Detection** | Identifies the language in which text is written. |
+| **Named Entity Recognition** | Identifies and categorizes entities in text, such as people, places, organizations, dates, and quantities. |
+| **PII Redaction** | Detects and redacts personally identifiable information (PII) such as names, addresses, and phone numbers. |
 | **Text Analytics for Health** | Extracts and labels medical entities (such as diagnoses, medications, and symptoms) from clinical text. |
-| **Conversational Language Understanding** | Interprets user utterances to identify intents and extract entities based on a trained custom model. |
-| **Custom Question Answering** | Returns curated answers to user questions from a configured knowledge base. |
 
-When you connect the Language MCP server to an agent, the agent receives the full list of available tools. Based on the user's prompt, the agent's underlying model decides which tool (or combination of tools) to call. For example, if a user asks "Summarize this article and tell me what people are mentioned," the agent might call both the summarization tool and the named entity recognition tool in the same turn.
+> [!NOTE]
+> Azure Language also provides functionality for sentiment analysis, summarization, key phrase extraction, and other common language-related tasks. These deprecated capabilities are provided to support existing applications.
+
+When you connect the Language MCP server to an agent, the agent receives the full list of available tools. Based on the user's prompt, the agent's underlying model decides which tool (or combination of tools) to call. For example, if a user asks "Determine the language that this article is written in, and tell me what people are mentioned." the agent might call both the language detection tool and the named entity recognition tool in the same turn.
 
 ## How the agent selects tools
 

learn-pr/wwl-data-ai/develop-text-analysis-agent-language-mcp/includes/03-connect-use-language-mcp.md

@@ -39,7 +39,7 @@ The agent now has access to all the text analysis tools exposed by the Azure Lan
 After connecting the Language MCP tool, update the agent's instructions to direct it to use the tool:
 
 ```
-You are an AI agent that assists users by helping them analyze and summarize text. Use the Azure Language tool to perform text analysis tasks.
+You are an AI agent that assists users by helping them analyze text. Use the Azure Language tool to perform text analysis tasks.
 ```
 
 This instruction helps the agent understand that it should use the connected tool when processing text analysis requests.
@@ -50,7 +50,7 @@ The agent playground in the Foundry portal provides an interactive environment f
 
 When you send a prompt that requires text analysis, the agent:
 
-1. Identifies the tasks needed (for example, summarization and entity recognition).
+1. Identifies the tasks needed (for example, language detection and entity recognition).
 1. Calls the appropriate Azure Language MCP tool(s).
 1. Returns a combined response.
 
@@ -84,7 +84,7 @@ response = openai_client.responses.create(
 print(response.output_text)
 ```
 
-The agent processes the prompt, calls the appropriate MCP tools, and returns the result in `output_text`. You can also inspect the full response JSON (using `response.model_dump_json()`) to see which tools the agent called — for example, `extract_named_entities_from_text` or `detect_sentiment_from_text` — along with the arguments and results for each tool call.
+The agent processes the prompt, calls the appropriate MCP tools, and returns the result in `output_text`. You can also inspect the full response JSON (using `response.model_dump_json()`) to see which tools the agent called — for example, `extract_named_entities_from_text` or `detect_language_from_text` — along with the arguments and results for each tool call.
 
 ### Connect the MCP server in code
 
@@ -108,6 +108,6 @@ When a user's prompt involves multiple text analysis tasks, the agent can call m
 
 > "Tell me what entities and dates are mentioned in this review, and whether it is positive or negative."
 
-This prompt requires both entity recognition and sentiment analysis. The agent identifies both tasks, calls the appropriate tools (`extract_named_entities_from_text` and `detect_sentiment_from_text`), and combines the results into a single response.
+This prompt requires both entity recognition and sentiment analysis. The agent identifies both tasks, calls the appropriate tools (`extract_named_entities_from_text` and `detect_language_from_text`), and combines the results into a single response.
 
 Each tool call goes through the MCP server independently, and the agent synthesizes the outputs into a coherent answer for the user.

learn-pr/wwl-data-ai/develop-text-analysis-agent-language-mcp/includes/04-exercise.md

@@ -1,6 +1,6 @@
 Now it's your turn to build a text analysis agent using the Azure Language MCP server!
 
-In this exercise, you create an AI agent in Microsoft Foundry, connect it to the Azure Language MCP server, test it in the agent playground, and build a Python client application that uses the agent to perform text analysis tasks such as entity recognition, sentiment analysis, and summarization.
+In this exercise, you create an AI agent in Microsoft Foundry, connect it to the Azure Language MCP server, test it in the agent playground, and build a Python client application that uses the agent to perform text analysis tasks such as entity recognition and PII redaction.
 
 > [!NOTE]
 > To complete this exercise, you need an **[Azure subscription](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn)** in which you have administrative access.

learn-pr/wwl-data-ai/develop-text-analysis-agent-language-mcp/index.yml

@@ -2,15 +2,15 @@
 uid: learn.wwl.develop-text-analysis-agent-language-mcp
 metadata:
   title: Develop a Text Analysis Agent with the Azure Language MCP Server
-  description: Learn how to build an AI agent that uses the Azure Language MCP server to perform text analysis tasks like entity recognition, sentiment analysis, and summarization.
+  description: Learn how to build an AI agent that uses the Azure Language MCP server to perform text analysis tasks like language detection, entity recognition, and personal information redaction.
   ms.date: 03/13/2026
   author: ivorb
   ms.author: berryivor
   ms.topic: module-standard-task-based
   ms.service: azure-ai-language
   ai-usage: ai-generated
 title: Develop a text analysis agent with the Azure Language MCP server
-summary: Learn how to build an AI agent that uses the Azure Language MCP server to perform text analysis tasks like entity recognition, sentiment analysis, and summarization.
+summary: Learn how to build an AI agent that uses the Azure Language MCP server to perform text analysis tasks like language detection, entity recognition, and personal information redaction.
 abstract: |
   After completing this module, you'll be able to:
   - Describe the Azure Language MCP server and the text analysis capabilities it exposes.
@@ -24,22 +24,22 @@ prerequisites: |
   - Have some familiarity with Python programming.
 iconUrl: /learn/achievements/generic-badge.svg
 levels:
-- intermediate
+  - intermediate
 roles:
-- ai-engineer
-- developer
+  - ai-engineer
+  - developer
 products:
-- language-service
-- microsoft-foundry
-- foundry-agent-service
+  - language-service
+  - microsoft-foundry
+  - foundry-agent-service
 subjects:
-- artificial-intelligence
+  - artificial-intelligence
 units:
-- learn.wwl.develop-text-analysis-agent-language-mcp.introduction
-- learn.wwl.develop-text-analysis-agent-language-mcp.understand-language-mcp
-- learn.wwl.develop-text-analysis-agent-language-mcp.connect-use-language-mcp
-- learn.wwl.develop-text-analysis-agent-language-mcp.exercise
-- learn.wwl.develop-text-analysis-agent-language-mcp.knowledge-check
-- learn.wwl.develop-text-analysis-agent-language-mcp.summary
+  - learn.wwl.develop-text-analysis-agent-language-mcp.introduction
+  - learn.wwl.develop-text-analysis-agent-language-mcp.understand-language-mcp
+  - learn.wwl.develop-text-analysis-agent-language-mcp.connect-use-language-mcp
+  - learn.wwl.develop-text-analysis-agent-language-mcp.exercise
+  - learn.wwl.develop-text-analysis-agent-language-mcp.knowledge-check
+  - learn.wwl.develop-text-analysis-agent-language-mcp.summary
 badge:
   uid: learn.wwl.develop-text-analysis-agent-language-mcp.badge