Merge pull request #7147 from PatrickFarley/task-adherence

Task adherence

Author: JillGrant615

articles/ai-services/.openpublishing.redirection.ai-services.json

@@ -170,6 +170,16 @@
       "redirect_url": "/azure/ai-foundry/ai-services/content-safety-overview?context=/azure/ai-services/content-safety/context/context",
       "redirect_document_id": false
     },
+    {
+      "source_path_from_root": "/articles/ai-services/content-safety/concepts/task-adherence.md",
+      "redirect_url": "/azure/ai-services/content-safety/overview",
+      "redirect_document_id": false
+    },
+    {
+      "source_path_from_root": "/articles/ai-services/content-safety/quickstart-task-adherence.md",
+      "redirect_url": "/azure/ai-services/content-safety/overview",
+      "redirect_document_id": false
+    },
     {
       "source_path_from_root": "/articles/ai-services/speech-service/how-to-custom-voice-create-voice.md",
       "redirect_url": "/azure/ai-services/speech-service/professional-voice-train-voice",

articles/ai-services/content-safety/concepts/task-adherence.md

@@ -52,7 +52,6 @@ This service makes several different types of analysis available. The following
 | Custom categories (rapid) API (preview) | Lets you define emerging harmful content patterns and scan text and images for matches. | [Custom categories concepts](/azure/ai-services/content-safety/concepts/custom-categories)| [How-to guide](./how-to/custom-categories-rapid.md) |
 | [Analyze text](/rest/api/contentsafety/text-operations/analyze-text) API   | Scans text for sexual content, violence, hate, and self harm with multi-severity levels. | [Harm categories](/azure/ai-services/content-safety/concepts/harm-categories)| [Quickstart](/azure/ai-services/content-safety/quickstart-text) |
 | [Analyze image](/rest/api/contentsafety/image-operations/analyze-image) API  | Scans images for sexual content, violence, hate, and self harm with multi-severity levels. | [Harm categories](/azure/ai-services/content-safety/concepts/harm-categories)| [Quickstart](/azure/ai-services/content-safety/quickstart-image) |
-| Task adherence API  | Detects when tool use by AI agents is misaligned, unintended, or premature in the context of a user interaction. | [Task adherence concepts](/azure/ai-services/content-safety/concepts/task-adherence)| [Quickstart](/azure/ai-services/content-safety/quickstart-task-adherence) |
 
 
 ## Content Safety Studio
@@ -140,8 +139,7 @@ See the following list for the input requirements for each feature.
   - Default minimum length: 110 characters (for scanning LLM completions, not user prompts).
 - **Custom categories (standard) API (preview)**:
   - Maximum inference input length: 1K characters.
-- **Task adherence (preview)**:
-  - Maximum input length: 100K characters.
+
 
 ### Language support
 

articles/ai-services/content-safety/includes/quickstarts/foundry-quickstart-task-adherence.md

@@ -23,8 +23,6 @@ items:
     href: concepts/groundedness.md
   - name: Protected material detection
     href: concepts/protected-material.md
-  - name: Task Adherence
-    href: concepts/task-adherence.md
   - name: Custom categories (preview)
     href: concepts/custom-categories.md
   - name: Harm categories
@@ -41,8 +39,6 @@ items:
     href: quickstart-protected-material.md
   - name: Protected material detection for code (preview)
     href: quickstart-protected-material-code.md
-  - name: Task adherence (preview)
-    href: quickstart-task-adherence.md
   - name: Custom categories (preview)
     href: quickstart-custom-categories.md
   - name: Text moderation