You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: copilot/manage-public-web-access.md
+4-14Lines changed: 4 additions & 14 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -14,7 +14,7 @@ ms.collection:
14
14
- magic-ai-copilot
15
15
- must-keep
16
16
hideEdit: true
17
-
ms.date: 05/05/2025
17
+
ms.date: 06/04/2025
18
18
---
19
19
20
20
# Data, privacy, and security for web search in Microsoft 365 Copilot and Microsoft 365 Copilot Chat
@@ -49,16 +49,6 @@ The user's prompts and Copilot's responses are stored within Microsoft 365 and n
49
49
50
50
After Microsoft 365 Copilot and Microsoft 365 Copilot Chat receive additional information from the Bing search service, this information is used to compose the response returned to the user.
51
51
52
-
When a Microsoft 365 Copilot user submits their prompt with the **Web content** toggle (that is, web search) turned on, they may receive two separate responses:
53
-
54
-
1. If resources are found within Microsoft 365, the user sees:
55
-
-**From your company's resources, emails, Teams messages, etc.**
56
-
57
-
2. If resources are found outside of Microsoft 365, the user sees:
58
-
-**From the web:**
59
-
60
-
The user can see results from both. Additionally, if the results are from the web only, the user sees the same **From the web:** heading.
61
-
62
52
### Web search query citations
63
53
64
54
To provide greater visibility into the generated search queries, web search query citations are shown to users in the linked citation section of the Copilot response. The section shows the exact web search queries (derived from the user’s prompt) that were sent to the Bing search service. Showing the exact web search queries helps users understand what search queries, along with the sites searched, were used to enhance Copilot’s response to their prompt. This information can help users improve their prompts and use Copilot more effectively.
@@ -67,7 +57,7 @@ Web search query citations are available only in Microsoft 365 Copilot Chat (pre
67
57
68
58
### Web search query logging
69
59
70
-
Web search query logging is available so that admins can perform search, audit, and eDiscovery on the exact web search queries Copilot derived from the user's prompt. Admins can already perform these actions for prompts and responses and will be able to use their familiar tools to extend those actions to search queries. For more information, see [Audit log activities](/purview/audit-log-activities#copilot-activities), [Copilot interaction events overview](/office/office-365-management-api/copilot-schema), and [Search for and delete Copilot data in eDiscovery (preview)](/purview/edisc-search-copilot-data#identifying-web-queries-in-microsoft-365-copilot-usage).
60
+
Web search query logging is available so that admins can perform search, audit, and eDiscovery on the exact web search queries Copilot derived from the user's prompt. Admins can already perform these actions for prompts and responses and are able to use their familiar tools to extend those actions to search queries. For more information, see [Audit log activities](/purview/audit-log-activities#copilot-activities), [Copilot interaction events overview](/office/office-365-management-api/copilot-schema), and [Search for and delete Copilot data in eDiscovery (preview)](/purview/edisc-search-copilot-data#identifying-web-queries-in-microsoft-365-copilot-usage).
71
61
72
62
### Examples of generated search queries
73
63
@@ -101,7 +91,7 @@ The [Product Terms](https://www.microsoft.com/licensing/terms/product/Privacyand
101
91
- They aren’t used to create advertising profiles or to track user behavior.
102
92
- They aren't shared with advertisers.
103
93
- They aren’t used to train generative AI foundation models.
104
-
- They are treated as customer confidential information and protected by appropriate technical and organizational measures.
94
+
- They're treated as customer confidential information and protected by appropriate technical and organizational measures.
105
95
106
96
The Bing search service operates separately from Microsoft 365 and has different data-handling practices. The web search queries generated by Copilot and sent to Bing are subject to the [Microsoft Services Agreement](https://www.microsoft.com/servicesagreement) between each user and Microsoft, together with the [Microsoft Privacy Statement](https://www.microsoft.com/privacy/privacystatement).
107
97
@@ -136,7 +126,7 @@ If the IT admin doesn’t configure the **Allow web search in Copilot** policy,
136
126
> For Government Community Cloud (GCC) customers:
137
127
> - Web search is available in GCC.
138
128
> - The **Allow web search in Copilot** policy is available in GCC in Cloud Policy service for Microsoft 365.
139
-
> - If the IT admin doesn’t configure the **Allow web search in Copilot** policy, web search will be turned off in GCC, regardless of how the **Allow the use of additional optional connected experiences in Office** policy is configured.
129
+
> - If the IT admin doesn’t configure the **Allow web search in Copilot** policy, web search is turned off in GCC, regardless of how the **Allow the use of additional optional connected experiences in Office** policy is configured.
140
130
141
131
### Web content toggle for users (only for Microsoft 365 Copilot)
|Teams channel meeting ([Teams New Calendar](https://support.microsoft.com/office/get-started-with-the-new-calendar-in-microsoft-teams-98f3b637-5da2-43e2-91b3-f312ab3e4dc5))|Cloud Policy: **Create and view Loop files in Microsoft apps that support Loop** -or- **Create and view Loop files in Outlook**|SharePoint Site: 📁`Meetings`|
Copy file name to clipboardExpand all lines: microsoft-365/syntex/document-understanding-overview.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -39,12 +39,12 @@ Use the unstructured document processing model ([teaching method](create-syntex-
39
39
40
40
## Introduction to unstructured models
41
41
42
-
The unstructured document processing model uses artificial intelligence (AI) to process documents. These documents must have text that can be identified based on phrases or patterns. The identified text designates both the type of file it is (its classification) and what you'd like to extract (its extractors).
42
+
Unstructured document processing models use artificial intelligence (AI) to analyze and extract information from documents. These models rely on identifiable text—based on phrases or patterns—to determine both the document’s classification and the data to extract.
43
43
44
44
> [!NOTE]
45
45
> For more information about how to use Syntex and scenario examples, see [Get started driving adoption of Microsoft Syntex](./adoption-getstarted.md) and [Scenarios and use cases for Microsoft Syntex](./adoption-scenarios.md).
46
46
47
-
Unstructured document processing models are created and managed in a type of SharePoint site called a [content center](create-a-content-center.md). When applied to a SharePoint document library, the model is associated with a content type has columns to store the information being extracted. The content type you create is stored in the SharePoint content type gallery. You can also choose to use existing content types to use their schema.
47
+
You create and manage unstructured document processing models in a SharePoint content center. When you apply a model to a SharePoint document library, it’s associated with a content type that includes columns for storing extracted information. You can create a new content type or use an existing one from the SharePoint content type gallery.
48
48
49
49
> [!NOTE]
50
50
> Read-only or sealed content types can't be updated, so they can't be used in a model.
@@ -55,7 +55,7 @@ Add [classifiers](create-a-classifier.md) and [extractors](create-an-extractor.m
55
55
56
56
- Extractors pull information from these documents. For example, for each contract renewal document identified in your document library, columns display that show the *Service Start Date* and *Client* for each document.
57
57
58
-
You can use example files to train and test your classifiers and extractors in your model. Example files provide your model examples of what to look for when trying to identify and extract data from files. For example, you would train your contract renewal classifiers and extractors with examples of contract renewal documents your company works with. You can also use example files to test the effectiveness of your model.
58
+
Use example files to train and test your classifiers and extractors. These files help the model learn what to look for when identifying and extracting data. For example, train your contract renewal model using real contract renewal documents from your organization. You can also use these files to validate your model’s accuracy.
59
59
60
60
After publishing your model, use the content center to apply it to any SharePoint document library that you have access to.
Copy file name to clipboardExpand all lines: microsoft-365/syntex/form-processing-overview.md
+9-11Lines changed: 9 additions & 11 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,7 +4,7 @@ ms.author: chucked
4
4
author: chuckedmonson
5
5
manager: jtremper
6
6
ms.reviewer: ssquires
7
-
ms.date: 01/22/2025
7
+
ms.date: 03/22/2025
8
8
audience: admin
9
9
ms.topic: concept-article
10
10
ms.custom: intro-overview
@@ -38,28 +38,26 @@ Use the freeform document processing model ([freeform selection method](create-s
38
38
39
39
## Introduction to structured and freeform models
40
40
41
-
Microsoft Syntex uses Microsoft Power Apps [AI Builder](/ai-builder/form-processing-model-overview) document processing to create structured and freeform document processing models within SharePoint document libraries.
You can use AI Builder document processing to create structured or freeform document processing models that use machine learning technology to identify and extract key-value pairs and table data from structured or semi-structured documents, such as forms and invoices, and unstructured or freeform documents, such as contracts and correspondence.
41
+
Microsoft Syntex uses Microsoft Power Apps [AI Builder](/ai-builder/form-processing-model-overview) to enable both structured and freeform document processing directly within SharePoint document libraries.
46
42
47
-
Organizations often receive invoices in large quantities from various sources, such as mail, fax, and email. Processing these documents and manually entering them into a database can take a considerable amount of time. By using AI to extract the text, key-value pairs, and tables from your documents, Syntex automates this process.
43
+
With AI Builder, you can create models that use machine learning to identify and extract key-value pairs and table data from various document types—including structured or semi-structured formats like forms and invoices, as well as unstructured formats like contracts and correspondence.
44
+
45
+
For example, organizations often receive large volumes of invoices through mail, fax, or email. Manually processing and entering this data can be time-consuming. Syntex streamlines this process by using AI to extract text, key-value pairs, and tables—automating data capture and reducing manual effort.
48
46
49
47
> [!NOTE]
50
48
> For more ideas about how to use these models in your organization, see [Get started driving adoption](adoption-getstarted.md) and [Scenarios and use cases](adoption-scenarios.md).
51
49
52
-
For example, you can create a structured or freeform document processing model that identifies all documents that are uploaded to the document library. From each document, you can then extract and display specific data that is important to you.
50
+
You can create structured or freeform document processing models that automatically identify and extract important information from files uploaded to a SharePoint document library.
53
51
54
52
55
53
56
-
You use example files to train your model and define the information to be extracted from your form. The layout of your document is learned by training your model. You only need five form documents to get started. Syntex analyzes your example files for key-value pairs, and you can also manually identify ones that might not have been detected. AI builder lets you test the accuracy of your model on your example files.
54
+
To get started, you use example files to train your model. Microsoft Syntex uses these examples to learn the layout of your documents and identify key-value pairs and tables. You only need five sample documents to begin. During training, you can review and manually tag any fields that weren’t automatically detected. AI Builder also lets you test your model’s accuracy using your example files.
57
55
58
-
You can only create a structured or freeform document processing model in SharePoint document libraries for which it's enabled. If it's been enabled, you're able to see the **Classify and extract** option in your document library.
56
+
You can only create document processing models in SharePoint libraries where Syntex has been enabled. If it’s available, yousee the **Classify and extract** option in the library’s command bar.
59
57
60
58
61
59
62
-
If you need it enabled on your document library, contact your Microsoft 365 admin.
60
+
If you don’t see this option, contact your Microsoft 365 admin to enable Microsoft Syntex for your library.
![m365-skilling-repo-management[bot]](https://avatars.githubusercontent.com/in/1161012?v=4&size=40){kind=avatar}
0 commit comments