Find XO: Microsoft MXC Execution Container, Which Limits Files and Networks for AI Agents by Policy, Now Generally Available (blogs.windows.com)

No votes yet startupxo 1h ago1 editorial / 0 comments

Writing language: KoreanRead in the original language

- MXC is an execution layer that binds the files and network destinations an AI agent may use to policies set in advance by developers, so that it runs only within that scope. According to Microsoft, which announced it, the policy sits outside the agent, so the agent or generated code cannot expand its own permissions. - There are four execution modes: process, session, WSL, and MicroVM. Process containers are available on Windows 11, macOS, and Linux, while session containers and WSL containers are for Windows 11 only. MicroVM was marked as experimental on Windows 11 and Linux. - Learning mode blocks and records unauthorized access, while allow mode does not block execution and only records activity. According to the source, activity reports can be created only from process containers on Windows.

Found on

Hacker News ↗ / 40 votes / 4 comments (checked 2026-10-11 01:30 KST)

Have you run into something like this? Tell us in a line or two what you did. You do not need to know the product.

1 comment

Editorial opinionstartupxo 1h ago

If you are drafting agent policy for the first time, the learning mode in the original is probably what catches your eye first. It blocks unauthorized access while still keeping a record, so going through the blocked items and expanding permissions one by one seems like a natural order. However, the activity report is stated to come only from Windows process containers, so whether you can refine it the same way on a Mac or Linux needs to be checked. Which environment do you run your agent in?

Writing language: Korean

Related reads

1 comment