Team knowledge base in SharePoint: Copilot compiles it, agents ground on it

Wed, 14 Oct 2026 07:00:00 +0200

On October 14, 2026, Microsoft announced a “team knowledge base” on the SharePoint blog. Copilot compiles a team’s content into a knowledge base of its own: a library of linked Markdown files that people can read and agents use for grounding. It starts as a Frontier preview and runs on usage-based billing.

This is the most interesting SharePoint announcement I’ve seen in a while, because it changes what an agent bases its answers on. It’s also the one I have the most questions about.

What’s actually new

Until now, grounding in Microsoft 365 meant retrieval. Copilot or an agent looks for passages in the original documents that match the question and builds an answer from them. The Knowledge Agent in SharePoint improved those documents with metadata and structure, but the answer still came from the originals.

The team knowledge base adds a layer in between. Copilot reads the team’s content and compiles it into a separate knowledge base: a special library of Markdown files that link to each other and are structured so agents can work with them easily. The component doing the compiling is the “Knowledge Compilation Engine”, part of Work IQ. If you want a quick refresher on where Work IQ sits, I covered it briefly in my post on RAG and Foundry IQ.

With retrieval, the knowledge is reassembled from raw data on every request. In the knowledge base, it already exists as a processed artifact you can open, read and correct. An agent no longer has to piece its answer together from twenty versions of the same slide deck.

How it works

It starts with a deliberate choice by the team: members pick the emails, chats, meetings and site content they want to contribute. The Knowledge Compilation Engine turns that into linked Markdown files, and from then on Copilot keeps them up to date. Both Copilot and agents can create, extend and curate the knowledge base, so think of it as a living library that keeps changing after the first run.

You can attach a knowledge base to any SharePoint site, including sites behind Teams channels and Microsoft 365 groups. In most tenants, that’s where the real teamwork happens.

There are two ways in: Copilot in SharePoint, and the Autopilot in the new Copilot app. Through the Autopilot you can also reach it from Teams, or simply send the Autopilot an email. The Autopilot rolls out separately, though, so turning on the knowledge base doesn’t mean your users have it.

On performance, Microsoft quotes its own internal tests from October 2026: agent responses up to 4x faster and 30% more token-efficient with the knowledge base. Those are vendor numbers. I wouldn’t put them into a business case before reproducing them with my own content.

Microsoft’s example scenarios cover three teams. Legal gets a knowledge base around its contracts. Engineering gets context for coding agents and an easier onboarding path for new team members. Sales gets account snapshots. The engineering case is the one I find most compelling: a coding agent that knows the architecture decisions from the Teams channel should write more useful code than one that only sees the repo.

Availability and licensing

As of today, the team knowledge base is available only in the Frontier preview and only for users on usage-based billing. Admins control it in the Microsoft 365 admin center. Microsoft says explicitly that the billing terms may change before general availability.

In practice, there’s no fixed per-license price, cost depends on usage, and the rules for that usage aren’t final yet. For a pilot, I’d pick a team with a manageable, well-maintained set of content. The department site with ten years of leftovers is a poor place to start.

Roadmap

Microsoft has announced several next steps, none of them with dates:

knowledge bases in Cowork, in Copilot in Teams and in Copilot Studio agents
deeper Microsoft 365 group integration, including bootstrapping a knowledge base from channels and mail
automatic curation through Copilot Studio agent flows
scaling to larger content sets with an approach called “Corpus Map”
integration with CLIs and coding agents through Work IQ

The same announcement bundled a handful of other SharePoint updates. Copilot in SharePoint is now generally available and the SharePoint tools in Work IQ are available. On top of that come a SharePoint Admin Agent, catalog management, a file-level permissions report for EEEU (“Everyone except external users”), insights into agent access, and a governance hub for site owners. I’d look at the EEEU report and the agent access insights first. They help you find overshared content before it ends up in a knowledge base.

My take: the open questions

Many of the organizations I work with are in regulated sectors, either critical infrastructure (KRITIS in Germany) or in scope for NIS2. For them, a feature like this stands or falls on questions the announcement doesn’t answer. I’m framing them as questions on purpose, because I don’t know the answers yet.

Permissions. The Markdown files are new files in a library. Do they inherit the permissions of their sources, or those of the library? What happens when an email goes in that only part of the team was allowed to read? Does the whole team then see the summary derived from it?

Sensitivity labels. Does a file compiled from a document labeled confidential carry that label? And which label applies when one file merges content from several sources with different labels? Mail and chats make this harder, because labeling there often works differently than in document libraries.

Retention. Mail, chats and site content are often covered by different retention policies. When the original is deleted at the end of its retention period, is the derived content removed too? Or does it live on in the knowledge base under the library’s rules? For deletion obligations and eDiscovery, that’s a big difference.

Cost control. If Copilot keeps the knowledge base current in the background, how much consumption does that generate when nobody is asking questions? Can you cap usage per site or per team, and how well can you estimate up front what a pilot will cost?

One tool already exists: in the Microsoft 365 admin center, Copilot > Cost Management lets you set spending policies with organization-level and per-user limits (Microsoft Learn). The “Auto-apply new services” setting is on by default, so newly supported services fall under existing policies automatically. The announcement doesn’t say whether the knowledge base shows up there as a service of its own. If you want to review new features before they’re covered, turn that setting off in the relevant policies.

Until those are answered, I wouldn’t attach a knowledge base to any site holding regulated or personal data. A pilot with non-sensitive content is a different matter, and I’d start one.

Conclusion

The team knowledge base is a real architectural shift: agents ground on a curated, readable layer instead of going straight to raw documents. Whether that holds up in practice depends on how permissions, labels and retention carry over. That’s where I’d look first in the preview, ahead of the performance numbers.

SharePoint on DR.365