Merge pull request #270361 from PatrickFarley/content-safety-updates

add preview tags

Author: Jill Grant

articles/ai-services/content-safety/overview.md

@@ -47,9 +47,9 @@ There are different types of analysis available from this service. The following
 | :-------------------------- | :---------------------- |
 | Analyze text API          | Scans text for sexual content, violence, hate, and self harm with multi-severity levels. |
 | Analyze image API         | Scans images for sexual content, violence, hate, and self harm with multi-severity levels. |
-| Prompt Shields (new) | Scans text for the risk of a [User input attack](./concepts/jailbreak-detection.md) on a Large Language Model. [Quickstart](./quickstart-jailbreak.md) |
-| Groundedness detection (new) | Detects whether the text responses of large language models (LLMs) are grounded in the source materials provided by the users. [Quickstart](./quickstart-groundedness.md) |
-| Protected material text detection | Scans AI-generated text for known text content (for example, song lyrics, articles, recipes, selected web content). [Quickstart](./quickstart-protected-material.md)|
+| Prompt Shields (preview) | Scans text for the risk of a [User input attack](./concepts/jailbreak-detection.md) on a Large Language Model. [Quickstart](./quickstart-jailbreak.md) |
+| Groundedness detection (preview) | Detects whether the text responses of large language models (LLMs) are grounded in the source materials provided by the users. [Quickstart](./quickstart-groundedness.md) |
+| Protected material text detection (preview) | Scans AI-generated text for known text content (for example, song lyrics, articles, recipes, selected web content). [Quickstart](./quickstart-protected-material.md)|
 
 ## Content Safety Studio
 

articles/ai-services/content-safety/quickstart-groundedness.md

@@ -11,7 +11,7 @@ ms.date: 03/18/2024
 ms.author: pafarley
 ---
 
-# Quickstart: Groundedness detection 
+# Quickstart: Groundedness detection (preview)
 
 Follow this guide to use Azure AI Content Safety Groundedness detection to check whether the text responses of large language models (LLMs) are grounded in the source materials provided by the users.
 

articles/ai-services/content-safety/quickstart-jailbreak.md

@@ -11,7 +11,7 @@ ms.date: 03/15/2024
 ms.author: pafarley
 ---
 
-# Quickstart: Prompt Shields 
+# Quickstart: Prompt Shields (preview)
 
 Follow this guide to use Azure AI Content Safety Prompt Shields to check your large language model (LLM) inputs for both User Prompt and Document attacks.
 

articles/ai-services/content-safety/toc.yml

@@ -23,11 +23,11 @@ items:
     href: quickstart-text.md
   - name: Image moderation
     href: quickstart-image.md
-  - name: Prompt Shields (new)
+  - name: Prompt Shields (preview)
     href: quickstart-jailbreak.md
-  - name: Groundedness detection (new)
+  - name: Groundedness detection (preview)
     href: quickstart-groundedness.md
-  - name: Protected material detection
+  - name: Protected material detection (preview)
     href: quickstart-protected-material.md
 
 - name: Samples 

articles/ai-services/content-safety/whats-new.md

@@ -18,11 +18,11 @@ Learn what's new in the service. These items might be release notes, videos, blo
 
 ## March 2024
 
-### Prompt Shields
+### Prompt Shields public preview
 
 Previously known as **Jailbreak risk detection**, this updated feature detects User Prompt injection attacks, in which users deliberately exploit system vulnerabilities to elicit unauthorized behavior from large language model. Prompt Shields analyzes both direct user prompt attacks and indirect attacks that are embedded in input documents or images. See [Prompt Shields](./concepts/jailbreak-detection.md) to learn more.
 
-### Groundedness detection
+### Groundedness detection public preview
 
 The Groundedness detection API detects whether the text responses of large language models (LLMs) are grounded in the source materials provided by the users. Ungroundedness refers to instances where the LLMs produce information that is non-factual or inaccurate from what was present in the source materials. See [Groundedness detection](./concepts/groundedness.md) to learn more.