3 min read
Connecting Claude to Microsoft 365, Safely
Security teams keep saying no when users ask to connect Claude to email. The problem isn't access, it's granularity. Here's what a yes can look like.
7articles
Security
More articles
Security6 min read
My Claude Guardrails
Claude Code can access our internal systems. Here are the guardrails: the policies that decide what my AI agent can actually reach, all published in our policy catalog.
Security3 min read
Good policy is the hard part. So we're sharing ours.
The risk from AI agents isn't any one system — it's the path between them. Policy guards that path. It's hard to write — so we open-sourced a library of policies.
Security7 min read
Audit kept us honest. Agents don't care.
Audit worked because people feared getting caught. AI agents don't — so agent security must shift from audit to authorization across every system.
SecurityClaude Cowork8 min read
Securing Claude Cowork
A practical guide to rolling out Claude Cowork safely: restrict risky access paths, route MCP through a policy layer, and monitor what your agents actually do.
security2 min read
Agentic AI security: why legacy controls fail AI agents
Legacy security controls were built for humans, not AI agents — that's why agentic AI security and governance are breaking. Here's the gap, and how to close it.
Intent-Based Policies for AI
The policy model that closes the gap between what organizations mean and what their controls enforce.