Security · Confidential Computing · Trustworthy AI
I'm Pawan Khandavilli, a product leader working on confidential computing at Microsoft. I write about AI security, agent identity, and the trust boundaries behind consequential systems.
Explore by subject
Identity, delegation, tool permissions, and trustworthy execution for autonomous systems.
Explore the topic → 02Protecting data in use and turning infrastructure promises into verifiable evidence.
Explore the topic → 03Architecture and product judgment that make security an enabler of better outcomes.
Explore the topic →Start here
The agentic economy is scaling on software trust primitives that can't keep up. Hardware-rooted attestation via confidential computing is the missing layer.
Read essay →Five questions for tracing sensitive data and delegated authority through any security architecture, from payments to AI agents.
Read essay →MCP servers aggregate high-value credentials behind a weak trust boundary. TEEs can protect them with memory isolation and measured identity.
Read essay →Continue the conversation
I enjoy comparing notes with people building secure cloud, AI, payments, and products where trust has to be earned.