Microsoft Expands Project Perception to Secure AI Agents at Scale with Agent Identities and Risk Controls
Cole Medin · youtube · 2026-10-21
Cole Medin covers Microsoft's expansion of Project Perception, built on Agent 365, for securing AI agents across an enterprise.
- Every agent gets its own identity, access is scoped to the task, and agents are contained as risk changes—without stripping employees' approved access.
- Dynamic Permissions grants task-specific, time-bound access to supported resources.
- Risk-based access controls evaluate agent actions using current risk and policy; teams review and approve protections before enforcement.
- Framed via the author's own 'second brain' agent: manual review works for one agent, but enterprises need IT visibility into every agent, owner, and reach.
Note: the video is sponsored by Microsoft.
Related event: Microsoft Expands Project Perception, Treating AI Agents as Insider Risks(6 posts)→
More from coding & agent
- Screenshot table to Excel in PowerShell: LLM only locates, code does the rest — dfinke · 2026-10-21
- One line of PowerShell turns any screenshot table into real Excel data in 4 seconds — dfinke · 2026-10-21
- Screenshot to spreadsheet in 4 seconds with one line of PowerShell — dfinke · 2026-10-21
- A mitm proxy that rewrites robots.txt to Allow: all gets you really far — generativist · 2026-10-21
- Anaconda ships MCP to stop coding agents from hallucinating malicious dependency packages — anacondainc · 2026-10-21
- 5-person team uses Claude and 300+ agents to design 318,484 proteins in 64 hours — 141_1337 · 2026-10-21