Growing Contributor · Build With Her Magazine

Margaret Stokes

Founder & Inventor of Aurora-Lens · Aurora-Lens

Member since September 2026 Publishes weekly

Be the first to follow Margaret.

New Contributor2 new stories this month

Founder and inventor of Aurora-Lens, a runtime AI governance architecture built around admissibility before consequence. My work combines philosophy, AI architecture and persistent state governance, with a particular focus on ambiguity, authority, unresolved knowledge and the point at which AI systems should be required to stop.

Impact

2Articles

0Followers

10 minutesReading time published

Milestones

First Article

Growing Contributor

2 of 5 articles to Established Contributor

Topics

All Work

Articles by Margaret

2 published

When an AI Agent Verifies the Wrong Thing

An AI accounts-payable agent spots changed bank details, asks for confirmation, gets a convincing reply, and still sends the money to a fraudster. This story shows how Aurora-Lens keeps unresolved authority from being mistaken for verification, and why capable agents need a boundary they cannot reason their way around.

Margaret Stokes

Words Come Second to the World

I came to AI through curiosity, then became increasingly troubled by hallucinations, collapsed ambiguity and the difficulty of trusting systems that could produce confident but unsupported answers. That led me to build Aurora-Lens, a system designed to maintain a persistent world, preserve uncertainty when it cannot be resolved, and stop actions before unsupported claims become consequences.

Margaret Stokes

Your Work Deserves to Be Documented

Every system you built. Every decision you made. That's a story worth telling.

Submit a Story →