Would you let an AI agent edit your company's knowledge base?

AI agents are getting pretty good at finding information, summarizing documents, and answering questions. But what about letting them change the information itself?

Imagine an AI agent finds outdated onboarding instructions in your company's wiki. Should it be allowed to fix them immediately? Suggest an edit for someone to review? Or simply flag the problem and leave everything to a human?

We've been thinking about this while developing the XWiki MCP Server.

Our approach is to respect existing user permissions and keep write operations disabled by default. Administrators can enable them when needed.

But I'm curious where others would draw the line.

Would you trust an AI agent to update internal documentation, or would you always want a human to approve changes first?

And does your answer change depending on the type of information involved?