Skip to content

THR996 Theater Thu 19 Nov 17:30 PST

Your Agent Has Access. Now Prove What It Did.

Julian Kusenberg

Session description

Microsoft's catalogue description

AI agents don't just read enterprise data anymore. They act on it. In this fast-paced investigation, we follow a risky agent interaction from prompt to tool execution, then use Microsoft Purview to block sensitive data, trace agent activity, and reconstruct what happened with Audit and eDiscovery. You'll leave knowing which controls matter before, during, and after an agent acts.

Demo timestamps

Microsoft's player does not support links to a specific time, so open the recording and skip to the time shown.

  1. Skip to 2:00

    Dashboard for agent activity

    The speaker shows a dashboard early in the talk, in the context of proving what an agent did.

  2. Skip to 21:42

    Portal logging of agent actions

    The speaker tells attendees to look inside the portal and says a click will log those things.

Watch on-demand (opens in a new tab)

Resources named in the session

← All sessions