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/copilot-tuning-doc-generation.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -5,7 +5,7 @@ ms.author: jasonjoh
5
5
manager: calvind
6
6
ms.audience: ITPro
7
7
ms.reviewer: jwolk
8
-
ms.date: 06/17/2025
8
+
ms.date: 07/17/2025
9
9
ms.topic: how-to
10
10
ms.localizationpriority: medium
11
11
description: Learn how to use Copilot Tuning to build an AI model for document generation based on organizational knowledge.
@@ -33,9 +33,9 @@ Some example use cases include:
33
33
34
34
- You must have permission to use Copilot Tuning in Copilot Studio. <!-- TODO: Link to permission doc here if it exists -->
35
35
- A collection of original documents and corresponding final draft documents that are stored in SharePoint.
36
-
- A collection of change logs or specifications stored in SharePoint.
36
+
- A collection of changelogs or specifications stored in SharePoint.
37
37
- A structured version of required changes to provide in the supplementary field within Copilot Tuning.
38
-
-A minimum of 20 well-aligned pairs of reference documents to target pairs that reflect a representative range of changes you expect the system to handle.
38
+
-More than 20 well-aligned pairs of reference documents to target pairs that reflect a representative range of changes you expect the system to handle.
39
39
40
40
> [!IMPORTANT]
41
41
> Document generation supports working with the following file formats: .doc, .docx, .html, .md, or .pdf. Copilot Tuning only uses information found in text. Copilot Tuning document generation doesn't use information in images, tables, or unstructured web content in your documents.
@@ -55,7 +55,7 @@ The following are the high-level steps to configure a custom document generation
55
55
56
56
### Prepare a mapping file
57
57
58
-
Your knowledge source should have at least 20 example pairs of original files and corresponding final (draft) files. In this step, you prepare a CSV file that provides at least 20 examples of original files to final (draft) documents. Copilot Tuning uses these examples to fine-tune the generation logic, helping the model learn how your organization typically edits or adapts documents.
58
+
Your knowledge source should have more than 20 example pairs of original files and corresponding final (draft) files. In this step, you prepare a CSV file that provides more than 20 examples of original files to final (draft) documents. Copilot Tuning uses these examples to fine-tune the generation logic, helping the model learn how your organization typically edits or adapts documents.
59
59
60
60
Create a file named **mapping.csv** and store it in the root directory of your knowledge source. This file should have two columns:
Copy file name to clipboardExpand all lines: copilot/copilot-tuning-expert-qa.md
+3-5Lines changed: 3 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,7 +4,7 @@ author: danielabom
4
4
ms.author: danielabo
5
5
manager: calvind
6
6
ms.reviewer: jwolk
7
-
ms.date: 06/17/2025
7
+
ms.date: 07/16/2025
8
8
ms.topic: how-to
9
9
ms.localizationpriority: medium
10
10
description: Learn how to use Copilot Tuning to build an AI model for expert question & answer (Q&A).
@@ -29,19 +29,17 @@ You can use the model maker to fine-tune a model that can complete the following
29
29
30
30
## Limitations
31
31
32
-
The model supports various document formats, but there are specific limitations to consider when using your content.
32
+
The model supports various document formats, with the following specific limitations:
33
33
34
34
- Content must be stored in SharePoint and be in supported formats (.docx, .pdf, .aspx); elements like embedded images or tables aren't supported.
35
35
- Not intended for general productivity or web-wide knowledge queries; it's limited to tenant-specific content and not suitable for tasks like managing meetings or browsing general internet data.
36
36
- Depending on the snapshot time of training data, newer content must be enriched via Search.
37
37
38
-
While there's no minimum document count, better results are achieved with larger content sets; at least 20 documents are recommended for training.
39
-
40
38
## Prerequisites
41
39
42
40
Before you start, make sure that you have the following prerequisites in place:
43
41
44
-
1. You must have domain-specific content or documentation, such as legal playbooks, HR guidelines, technical documentation, policy manuals, or departmental procedures, that the model can use to answer questions.
42
+
1. You must have domain-specific content or documentation, such as legal playbooks, HR guidelines, technical documentation, policy manuals, or departmental procedures, that the model can use to answer questions. The content set that you use to train the model must consist of more than 20 files.
45
43
2. Configure the model agent with a Microsoft Entra ID security group or distribution list and create your own Entra ID groups to be added to the model.
46
44
3. Identify where your content is stored in SharePoint.
Copy file name to clipboardExpand all lines: copilot/copilot-tuning-knowledge-selection.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -5,7 +5,7 @@ author: msplants
5
5
ms.author: jwolk
6
6
manager: calvind
7
7
ms.topic: concept-article
8
-
ms.date: 06/17/2025
8
+
ms.date: 07/17/2025
9
9
ms.localizationpriority: medium
10
10
---
11
11
@@ -25,7 +25,7 @@ Selecting knowledge is the first and most critical step in Copilot Tuning. You s
25
25
26
26
-**Supported file formats and content:** All Copilot Tuning tasks support common text-based document formats. You can use Word documents (.doc, .docx), HTML files (.html, .aspx), Markdown files (.md), or PDF files processed by Optical Character Recognition (OCR) as source materials. You can also include Excel documents (.xls, .xlsx) for expert Q&A. The tuning process ingests the text content from these files. It doesn't learn from images, embedded tables, or other non-text elements in the documents. Ensure that the important information in your training documents is in textual form. For example, if a filePDF contains a chart, include a textual explanation of that chart's insights in the document.
27
27
28
-
-**Number of documents:** You must provide at least 20 samples (documents for Q&A and summarization; input-output pairs for document generation) to Copilot Tuning. Usually hundreds or thousands of samples is ideal, and you can provide a maximum of 10k. The quality of samples is more important than raw quantity. We highly suggest you focus you data preparation time on finding as many high quality samples that are well-aligned with what you expect your fine-tuned model to do.
28
+
-**Number of documents:** You must provide more than 20 samples (documents for Q&A and summarization; input-output pairs for document generation) to Copilot Tuning. Usually hundreds or thousands of samples is ideal, and you can provide a maximum of 10k. The quality of samples is more important than raw quantity. We highly suggest you focus you data preparation time on finding as many high quality samples that are well-aligned with what you expect your fine-tuned model to do.
29
29
30
30
-**Model instructions:** During the model configuration process, Copilot Tuning asks the model maker to provide answers to a series of model instructions to guide the system on how to use the knowledge you selected. Each task type has its own questions about the selected knowledge source. Prepare clear, structured answers to each question. Expert Q&A requires a description of the data in the knowledge source and how it's organized. Document generation requires you to specify how the original input, changes, and output draft document are referred to in your organization. Summarization requires you to specify how to refer to the summaries. It's important that this information is clear and accurately represents your data in order for the system to be most effective.
Copy file name to clipboardExpand all lines: copilot/manage-public-web-access.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -56,6 +56,8 @@ After Microsoft 365 Copilot and Microsoft 365 Copilot Chat receive additional in
56
56
57
57
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.
58
58
59
+
:::image type="content" source="media/copilot-web-search-citations-raw.png" alt-text="Screenshot of web search query citations in Microsoft 365 Copilot.":::
60
+
59
61
Web search query citations are available only in Microsoft 365 Copilot Chat (previously named Business Chat). Citations aren’t available in the Copilot pane within a Microsoft 365 app, such as Word or PowerPoint. Also, the web search queries are only available in the chat thread for 24 hours.
Copy file name to clipboardExpand all lines: copilot/people-skills-overview.md
+28-6Lines changed: 28 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,7 +6,7 @@ ms.author: anirudhbajaj
6
6
manager: dansimp
7
7
ms.service: microsoft-365-copilot
8
8
ms.topic: overview
9
-
ms.date: 05/29/2025
9
+
ms.date: 07/18/2025
10
10
---
11
11
12
12
# Overview of People Skills
@@ -30,11 +30,33 @@ People Skills comes with your Microsoft 365 Copilot or Viva licenses and doesn't
30
30
31
31
-**Microsoft 365 Copilot in Productivity Apps service plan**: Customers with the "Microsoft 365 Copilot in Productivity Apps service plan" can use People Skills, including AI-inferencing and related Copilot experiences, excluding education and government licenses.
32
32
33
-
For a detailed list of People Skills experiences and their corresponding license requirements, see the following diagram.
34
-
35
-
:::image type="content" source="media/people-skills-inferencing/people-skills-licensing.png" alt-text="Diagram that shows the list of People Skills experiences and their corresponding license requirements." lightbox="media/people-skills-inferencing/people-skills-licensing.png":::
36
-
37
-
If you have questions on licensing or access, contact your Microsoft representative.
33
+
## People Skills functionality access by license
34
+
35
+
For a detailed list of People Skills experiences and their corresponding license requirements, see the following table.
36
+
37
+
If you have questions about licensing or access, contact your Microsoft representative.
38
+
39
+
| Release | Functionality | Base SKU (ME3/ME5)*| M365 Copilot | Viva Suite | Viva Insights | Viva Learning |
Copy file name to clipboardExpand all lines: microsoft-365/admin/activity-reports/microsoft-copilot-usage.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
@@ -3,7 +3,7 @@ title: "Microsoft 365 admin center – Microsoft 365 Copilot Chat usage"
3
3
ms.author: camillepack
4
4
author: camillepack
5
5
manager: scotv
6
-
ms.date: 05/07/2025
6
+
ms.date: 07/16/2025
7
7
audience: Admin
8
8
ms.topic: concept-article
9
9
ms.service: microsoft-365-copilot
@@ -23,7 +23,7 @@ description: "Learn about the Microsoft 365 Copilot Chat usage report and gain i
23
23
The Microsoft 365 Copilot Chat usage dashboard provides insights into active usage of Microsoft 365 Copilot Chat. The report includes total active users, average daily active users, and active users per app. Usage insights can be viewed as totals and trends for the past 7, 30, 90, or 180-day periods. The report also shows the last activity date per user, anonymized by default. To view all reports, check out [Microsoft 365 Reports in the admin center overview](activity-reports.md).
24
24
25
25
> [!NOTE]
26
-
> The report is currently limited to users without a Microsoft 365 Copilot license that interact with Copilot Chat in Teams, Outlook, Copilot.cloud.microsoft, Microsoft 365 Copilot (app), and Microsoft Edge.
26
+
> The report is currently limited to users without a Microsoft 365 Copilot license that interact with Copilot Chat in Teams, Outlook, Copilot.cloud.microsoft, Microsoft 365 Copilot (app), Microsoft Edge, Word, Excel, and PowerPoint. The all-up Copilot Chat user count as well as the ‘last activity date’ for each user will reflect usage of Copilot Chat in all of these host apps. Initially the report will not provide a breakout of usage in Word, Excel, and PowerPoint, but this update is planned and will be available soon.
27
27
28
28
## How do I get to the Microsoft 365 Copilot Chat usage report?
29
29
@@ -80,7 +80,7 @@ You can also export the report data into an Excel .csv file by selecting the **E
|**Last activity date (UTC)**| The most recent date on which the user sent a message to Microsoft 365 Copilot Chat in Teams, Outlook, Copilot.cloud.microsoft, Microsoft Edge, or the Microsoft 365 Copilot (app). This date remains fixed even if the timeframe of the report is changed. |
83
+
|**Last activity date (UTC)**| The most recent date on which the user sent a message to Microsoft 365 Copilot Chat in Teams, Outlook, Copilot.cloud.microsoft, Microsoft Edge, the Microsoft 365 Copilot (app), Word, Excel, or PowerPoint. This date remains fixed even if the timeframe of the report is changed.|
84
84
|**Last activity date of Teams (UTC)**| The most recent date on which the user sent a message to Microsoft 365 Copilot Chat in Teams. This date remains fixed even if the timeframe of the report is changed. |
85
85
|**Last activity date of Outlook (UTC)**| The most recent date on which the user sent a message to Microsoft 365 Copilot Chat in Outlook. This date remains fixed even if the timeframe of the report is changed. |
86
86
|**Last activity date of Copilot.cloud.microsoft (UTC)**| The most recent date on which the user sent a message to Microsoft 365 Copilot Chat in Copilot.cloud.microsoft. This date remains fixed even if the timeframe of the report is changed. |
Copy file name to clipboardExpand all lines: microsoft-365/admin/email/configure-email-forwarding.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -33,7 +33,7 @@ As the admin of an organization, you might have company requirements to set up e
33
33
> [!IMPORTANT]
34
34
> You can use outbound spam filter policies to control automatic forwarding to external recipients. For more information, see [Control automatic external email forwarding in Microsoft 365](/microsoft-365/security/office-365-security/outbound-spam-policies-external-email-forwarding#how-the-outbound-spam-filter-policy-settings-work-with-other-automatic-email-forwarding-controls).
35
35
>
36
-
> Email forwarding to recipients outside the organization doesn't prevent messages identified as spam or phishing from being forwarded. The recipient needs their own email security filter to identify and block these messages.
36
+
> Email forwarding to external recipient domains outside the organization doesn't prevent messages identified as spam, phishing, or high-confidence phishing from being forwarded. The recipient needs their own email security filter to identify and block these messages.
0 commit comments