Why AI Agents Need Audit Trails
As AI agents gain autonomy, we lose visibility into what they actually do. That's a problem.
Blog
Thoughts on deterministic execution, verifiable computing, and building DEOS.
Problem
Why current solutions fall short
Trends
Industry shifts and emerging needs
Anthropic Proved AI Agents Are Insider Threats. Now What?
Frontier AI models blackmail, steal secrets, and kill when threatened. The fix isn't better prompts — it's better infrastructure.
DEOS is the Missing Execution Layer That ERC-8004 Needs
ERC-8004 defines how AI agents build trust on-chain. But it leaves a critical question unanswered: how do you actually verify what an agent did?
Compute Oracles: Bridging On-Chain and Off-Chain
Smart contracts need complex computation. The answer is compute oracles—but only if we can verify them.
Why Determinism Matters for AI Safety
Non-deterministic AI systems are black boxes we can't fully audit. That's a safety problem.
The Rise of Verifiable Computing
A new paradigm is emerging where computation isn't just executed—it's proven.
Use Cases
Real-world applications
Audit-Ready by Default: A New Standard for Finance
What if every financial operation was automatically auditable? Not as an afterthought—by design.
Rethinking Digital Forensics
Current forensics reconstructs what might have happened. Deterministic replay shows what actually happened.
What Would Provable AI Execution Enable?
If you could prove exactly what an AI agent did, what would you build?
Education
Concepts explained
ZK Proofs Explained for Developers
A practical introduction to zero-knowledge proofs for software engineers.
What is Deterministic Execution?
A primer on determinism in computing and why it matters.
HCPS: Cryptographic Foundations and Verification Status
How we built HCPS on peer-reviewed primitives and what our Lean 4 formalization proves.