Good social behaviors. Hard limits. Creative constraint.
_Who We Are
We come from applied cryptography and the security of high-stakes systems — MPC, ZK, biometric identity at global scale (Worldcoin, Aria). We bring that engineering bar to a new problem: making autonomous AI agents safe to deploy.
Aurel — CTO. Background in cryptography-heavy systems. The team scales frontier crypto into production-grade infrastructure for the agentic age.
_The Product
A control plane for AI agents.
It sits between agents and everything they touch. Credentials never reach the agent. Policies live in the runtime, not in prompts. Every action is annotated and signed at the boundary — not self-reported.
_Three Pillars
Verified at runtime, not promised in policy.
_The Question
The interesting part isn't bigger models — it's the scaffolding around them. The boundary where intent meets action. The runtime where data meets logic. The interface where humans stay in control without becoming the bottleneck. The economy that emerges when software stops looking like SaaS.
"Post-mortem: how an agent deleted our prod DB." Every credential checked out. Every tool call was authorised. The agent followed instructions — just not the ones we thought we'd given it. That's the failure mode the scaffolding has to prevent — structurally, not by asking nicely.
We've grouped the open problems into three conversations.
_Three Conversations
_Room 01
An agent is a loop of cognition + action. Wherever the loop touches the world, that boundary is where trust can be engineered — or lost.
If the LLM is allowed to be wrong half the time, where in the stack do we put the parts that can't be wrong?
Open thread: how do you protect honest-but-lazy users from themselves — e.g. copy-paste through the trust boundary?
Deep dive — Maller, CAPE: Context-Aware Private Execution · /CAPE.pdf
_Room 02
A control plane is only as good as the humans who configure it and the humans who review it. Real deployments have CTOs, security officers, compliance, and the operator — each with a different mental model.
What's the right unit of human approval — a tool call, a task, or a plan?
Open thread: nobody actually reads the logs. What would make them want to?
_Room 03
If software generates software, generic SaaS loses its moat. What replaces it — and what does it take to trust a codebase nobody fully read?
What's the sufficient set of criteria for a dev and an owner to feel safe with code they didn't write?
Open thread: when SaaS dies, what's the smallest unit of software a company still buys?
_Format
30 minutes per round. We reconvene to compare notes.
_Over to you