Projects / Agents in Intune / Chapter Three

Extending Agents Into a Coordinated, Multi-Agent System

Real security work spans the whole estate, not one product — and needed agents that could coordinate across that boundary. Microsoft’s own framing for the answer: strategy stays human, scale becomes autonomous.

At a glance
Role
Foundational design contributor
Scope
Multi-agent coordination across the estate, not just Intune
Outcome
Entered limited public preview, August 2026
Overview

“Introducing Project Perception: The Next Evolution of Agentic Security” — Microsoft Security, Microsoft’s official YouTube channel. Watch on YouTube for captions and transcript ↗

01 — The problem

Every agent so far had been governed within one product, Intune. But real security work crosses boundaries — an investigation might start in Defender, pull device context from Intune, and end with a policy change elsewhere in the estate — and nothing coordinated agents across that line or gave security a single place to direct and approve work spanning more than one product.

The audience shifted too: from the Intune admin managing devices, to security teams — Security Reader and Security Admin roles working in Defender on threat investigation and remediation.

02 — What I learned first

I contributed early, foundational design work on the interaction model. Two findings shaped it: coordination needed a shared, durable session — the same “revisitable artifact, not ephemeral chat” principle from the Intune agent work — not scattered, untraceable conversations. And security teams didn’t want to learn which specialized agent to open for a given task; they wanted to describe the goal and let the system route to the right one, with natural-language chat as the front door.

Project Perception chat entry point in the Microsoft Defender portal: "What do you want to do next?" with a task box and playbook cards, alongside Sessions, Playbooks, and Agents in the side nav
Chat as the front door, with Sessions and Playbooks as their own tabs alongside it — the shipped shape of that entry-point finding. Screenshot from Microsoft’s public preview announcement — microsoft.com/security/project-perception-agentic-system.
03 — Exploration

How far the system could act on its own, without a human re-approving every step, was the harder question. It doesn’t scale to sign off on individual actions across an entire security estate — but the fix wasn’t more automation with less oversight. It was moving where that oversight lives.

Ruled out

Approve every action individually

Approval-per-step works for one agent, one session — not a system meant to run continuously across multiple agents. Treated as a queue, it becomes exactly the bottleneck it was meant to remove.

Preview

Approve the strategy, not each step

Security teams approve the mission — what to watch for, what it’s allowed to act on. Review friction then scales with risk: clean actions get a single-click confirmation, flagged ones get escalated. Microsoft’s framing: “Strategy stays human. Scale becomes autonomous.”

Safety & Guardrail Flow

Risk-tiered response — review friction scales to severity, not a flat on/off for autonomy.

Incoming action

Script, policy change, or remediation request enters the pipeline.

Risk analysis

Agent evaluates harm potential, anomalies, and contextual signals.

Low risk

No risk detected

Signal is clean. Action is within expected parameters.

Review depth

1

Single-click approve

Admin sees a summary card — one button to approve.

2

Audit logged

Decision recorded with actor, timestamp, and context.

Action deployed

Proceeds immediately on approval.

Elevated

Risk detected

Anomaly or policy concern flagged. Human judgment required.

Review depth

1

Reasoning surface

Agent explains why this was flagged and what it found.

2

Full review form

Admin reads context, adds notes, approves or rejects.

3

Audit logged

Full reasoning chain and decision recorded.

Pending admin decision

Proceeds or is blocked based on the outcome.

High-risk

High-risk or destructive

Potentially catastrophic. Blocked immediately, escalated for review.

Review depth

1

Auto-block

Action is halted before any effect takes place.

2

Escalated review

Routed to a senior admin with full context and diff.

3

Threshold check

Configurable rules can pre-authorize known-safe destructive ops.

4

Audit logged

Block reason, escalation chain, and final decision recorded.

Blocked until resolved

Only proceeds on explicit escalation approval.

A design exploration of mine, not a confirmed Perception mechanism — shown to illustrate the “strategy stays human” tradeoff above in more depth.

04 — What shipped

What shipped is a framework Microsoft can keep extending, not just three agent teams working one case. Underneath sits what Microsoft calls the Harness — the orchestration layer that keeps every agent reliable and guided, so autonomy grows without losing the human checkpoint. Hosted in Microsoft Defender: Red probes like an attacker, Blue investigates like a responder, Green remediates — coordinated through one shared, auditable session instead of isolated chats.

Red teamSimulates attacks
Blue teamDetects and triages
Green teamFixes and remediates

Red, Blue, Green — Microsoft’s own framing for the three agent teams, not a naming convention I invented. Public preview, per Microsoft’s own announcement — microsoft.com/security/project-perception-agentic-system and the Official Microsoft Blog announcement.

05 — Tradeoffs I own

Approval checkpoints throughout the workflow cost real friction — every one is a chance to pause a plan already in motion. I designed for it anyway: with several agents acting in sequence, the ability to intervene mattered more than a faster run. One approval up front would have been simpler, but asked for more trust than a brand-new system had earned.

06 — Beyond this feature

This work started as a cross-platform initiative, not something scoped to Intune — so its scale and monitoring gaps were never just Intune’s to solve. Pushing the fix into the shared foundation strengthened what every product agent builds on, VRA included: solve the problem where you find it, then generalize it.

The ripple runs the other direction too: Perception’s continuous, proactive protection means a patch could land on an Intune admin’s own devices, approved by security, not by them. Pulling admins into that approval loop would recreate the same bottleneck ruled out in phase 03. My answer: configurable thresholds so an admin sets their own comfort level upfront, backed by the ability to audit and roll back after the fact.

07 — What I’d carry forward

A shared, durable session is worth the redesign cost once more than one agent touches an outcome — per-agent chat histories don’t hold up when agents hand off work.

Approval doesn’t have to mean stopping at every step — the harder, more valuable design problem is deciding which layer of the system the approval belongs at.

Patterns built for one product’s constraints often reveal gaps the wider system hasn’t hit yet — solve locally, then generalize, rather than waiting for someone else to find the same gap.