Table of Contents
AI-Generated Essential Meeting Insights Captured in Meeting Archive Files
In July, Microsoft published message center notification MC1429018 (last updated 21 September 2026, Microsoft 365 roadmap item 558933) to announce the introduction of AI-generated meeting archive files for Teams meetings. Meeting archives capture essential details about what happened during a meeting so that Copilot, Facilitator, and other “downstream Microsoft AI tools” (mentioned but not specified by the documentation) can answer questions about the meeting more efficiently. If an AI response uses information from a message archive, it is cited in the response just like any other file.
As often happens with new technology, the rollout has been delayed, and the current schedule predicts that tenants using targeted release will see the feature in early November 2026. General availability is scheduled for deployment in early December 2026 and be finished worldwide in early January 2027.
Meeting Policy Settings for Meeting Archives
Generation of meeting archive files is controlled by Teams meeting policy settings. The settings are available in the Teams admin center (Figure 1). By default, meeting archive generation is enabled.
The settings can be configured with PowerShell (Teams module 8.0 or later). This command enables meeting archive generation for accounts covered by the default meeting policy and sets the expiration period for meeting archive files to be 180 days (rather than the default 1825 days, which seems a tad excessive):
Set-CsTeamsMeetingPolicy -Identity Global -AllowMeetingKnowledgeGeneration $True -MeetingKnowledgeExpirationDays 180
It’s worth noting at this point that Purview retention policies take precedence over the retention period for meeting archive files configured in Teams meeting policies. Meeting archive files can be processed by retention policies configured for SharePoint classic and communication sites.
When enabled, Teams generates meeting archive files when three conditions are satisfied:
- Transcription is enabled for a meeting.
- At least one meeting participant has a Microsoft 365 Copilot licence.
- A sensitivity label with encryption is not assigned to the meeting.
- The meeting option “Allow Copilot and Facilitator” is set to “During and after the meeting”
In addition, Teams does not generate meeting archive files when meetings use end-to-end encryption, or the meeting settings restrict copying or forwarding.
Two New PowerShell Cmdlets
Speaking of PowerShell, the documentation discusses two new cmdlets:
- Get-AIGeneratedKnowledgeContainer: returns the URL of the SharePoint Embedded container used to store a meeting archive. Depending on the current load on the server, it can take several hours after a meeting is over before the meeting archive file is available.
- Remove-AIGeneratedKnowledge: removes the archive file for a meeting.
Both cmdlets take the chat thread identifier for a meeting as their primary parameter. To get the chat thread identifier, use the copy link option when viewing meeting properties. This copies the meeting link, which looks like this:
https://teams.microsoft.com/l/chat/19:meeting_NmNjMGJlODUtMGMyYi00ZTc5LTkyYzMtNmNiOWQxYTMyNDk1@thread.v2/conversations?context=%7B%22contextType%22%3A%22chat%22%7D
Edit the meeting link to extract the chat thread identifier. Taking the example above, the chat thread identifier is:
19:meeting_NmNjMGJlODUtMGMyYi00ZTc5LTkyYzMtNmNiOWQxYTMyNDk1@thread.v2
The thread identifier can then be used with the cmdlets. In this example, we remove a meeting archive file:
Remove-AIGeneratedKnowledge -ThreadId "19:meeting_NmNjMGJlODUtMGMyYi00ZTc5LTkyYzMtNmNiOWQxYTMyNDk1@thread.v2" AI generated knowledge has been successfully removed.
However, I discovered that the cmdlet takes any value and reports success when it runs, which isn’t very helpful:
$id = '18174' Remove-AIGeneratedKnowledge -ThreadId $id AI generated knowledge has been successfully removed.
The Get-AIGeneratedKnowledgeContainer cmdlet returns the URI to the SharePoint Embedded container where the meeting archive file is stored. Teams provisions 200 SharePoint Embedded containers to store meeting archive files and distributes the files across the containers. Here’s how to find the container URI for a meeting archive:
Get-AIGeneratedKnowledgeContainer -ThreadId '19:meeting_NmNjMGJlODUtMGMyYi00ZTc5LTkyYzMtNmNiOWQxYTMyNDk1@thread.v2'
If the file is available, you’ll see the URI for the container:
https://office365itpros.sharepoint.com/contentstorage/CSP_e227b4ff-a475-4d80-a486-788dfb700ee2
We can retrieve additional details of the container by using the Get-SPOContainer cmdlet from the SharePoint Online management module. Here’s how to do the job:
$MatchContainerUri = Get-AIGeneratedKnowledgeContainer -ThreadId '19:meeting_NmNjMGJlODUtMGMyYi00ZTc5LTkyYzMtNmNiOWQxYTMyNDk1@thread.v2'
If ($MatchContainerUri) {
[array]$Containers = Get-SPOContainer | Where-Object {$_.ContainerName -eq 'Meeting Artifacts'}
Write-Output "Checking SPE containers for meeting artifacts…"
ForEach ($Container in $Containers) {
$ContainerData = Get-SPOContainer -Identity $Container.ContainerId
If ($ContainerData.ContainerSiteUrl -eq $MatchContainerUri) {
Write-Output "Container details"
Write-Output "-----------------"
$ContainerData
}
}
}
The details of the container should look something like this:
RunspaceId : 6aa1427d-0558-426e-bcab-a826dc4be2d2
ContainerId : b!_7Qn4nWkgE2khniN-3AO4sX6aBxNKFZCjdc-dhUvs-9Z5UxCRXXET6-BptEJWrmf
ContainerName : Meeting Artifacts
Description : Container for Meeting Artifacts
OwningApplicationId : 00000000-0000-0000-0000-000000000000
OwningApplicationName : <<Unknown>>
ContainerApiUrl : https://office365itpros-admin.sharepoint.com/_api/v2.1/storageContainers/b!_7Qn4nWkgE2khniN-3AO4sX6aBxNKFZCjdc-dhUvs-9Z5UxCRXXET6-BptEJWrmf
ContainerSiteUrl : https://office365itpros.sharepoint.com/contentstorage/CSP_e227b4ff-a475-4d80-a486-788dfb700ee2
ContainerRedirectUrl :
SensitivityLabel :
Owners : {}
Managers : {}
Readers : {}
Writers : {}
CreatedOn : 16/08/2026 11:12:46
StorageUsedInBytes : 56179
ConditionalAccessPolicy : AllowFullAccess
AllowEditing : True
LimitedAccessFileType : WebPreviewableFiles
ReadOnlyForUnmanagedDevices : False
AuthenticationContextName :
RestrictContentOrgWideSearch : False
BlockDownloadPolicy : False
ReadOnlyForBlockDownloadPolicy : False
SharingDomainRestrictionMode : None
SharingAllowedDomainList :
SharingBlockedDomainList :
ArchiveStatus : NotArchived
ArchivedBy :
ArchivedTime : 01/01/0001 00:00:00
PrincipalOwner :
OwnershipType : ApplicationOwned
EnableRestrictedAccessControl : False
RestrictedAccessControlGroups :
InformationBarriersMode :
InformationSegment :
Unfortunately, as I discovered when I attempted to track down why a Loop container consumed so much valuable SharePoint storage quota, the Graph fileStorageContainer API only permits access to the items in SPE containers to the application which owns the containers. In this case, the application is Teams, so only Teams can access the meeting archive files. Given their role as archives, Microsoft obviously doesn’t want users to be able to mess with the files.
Using eDiscovery to Find Meeting Archive Files
Well, that’s not quite right, because Purview eDiscovery can find and export meeting archive files stored in SPE containers. Create a new content search and choose SharePoint Online sites as the source to search. The query is simple:
Filetype:"meeting"
If all goes well, the search will find the meeting archive files (Figure 2).
The file preview feature in eDiscovery can’t display the contents of the meeting archive files, but you can export the files found by the search. eDiscovery creates a ZIP file containing the items found and summary information. Figure 3 shows the meeting archive file downloaded from eDiscovery:
Meeting archive files are compressed but not encrypted. According to Microsoft, a meeting archive holds “AI-generated information designed to help Microsoft 365 Copilot understand previous meetings and bring richer context into future conversations” and can include:
- Decisions made during a meeting.
- Action items and follow-ups assigned during a meeting.
- Meeting summaries.
- Supporting context.
In practical terms, the compressed meeting file holds a file called transcripts.json holding the AI-generated information. Figure 4 shows some of the contents for a meeting where you can see how remarks made by participants are captured.
The structured nature of the meeting archive and the structured AI-processed knowledge it contains is designed to make it faster for Copilot and the Facilitator agent to ingest and use when prompted about what happened in the meeting later. Only meeting participants can benefit from the AI-generated insights stored in the meeting archive. In addition, Copilot can only use meeting archive files for users from the same tenant as the meeting organizer.
Time for a Governance Update
Like any new file created inside Microsoft 365, tenants should consider how meeting archive files figure in their data lifecycle and governance strategy. In particular, I’d look at reducing the 1825 default retention period. We know that most people never go near the recordings of Teams meetings after a month or so has passed. If that’s the case, what’s the point of keeping a meeting archive for any longer?
The nice thing about generative AI tools is that they can generate information based on what’s gone before. The bad thing about generative AI tools is that they can’t create new thinking or insights about how technology works (or doesn’t). When we write the Microsoft 365 for IT Pros eBooks, we depend on hundreds of years of real-world experience, knowledge, and intuition to analyze and explain how Microsoft 365 really works. If you understand the basic principles about Entra ID, Exchange Online, SharePoint Online, Teams, the Microsoft Graph, and more, you’ll be able to figure out the value of new features as Microsoft adds them to the platform. All for less than ten cups of black coffee.

