Certus - Liability insurance for AI agents. One line of code
by•
Your AI agent is one hallucination away from a lawsuit. Traditional insurers are filing exclusions for AI claims. Certus wraps your agent in a single line of code, generates cryptographic proof of every action it takes, scores risk in real-time. We’re building the verification and risk infrastructure that the AI agent economy needs.
This is the foundation that makes AI agents accountable - and eventually, insurable.
Safe agents pay less. Risky ones pay more. Like Tesla Insurance, but for AI.
Replies
Hey PH! I’m Sarthak, building Certus.
Here’s the problem: AI agents are making real decisions - booking flights, processing refunds, writing code, sending emails. When they screw up (and they do), nobody knows exactly what happened, and your insurance company won’t cover it. AIG, Great American, and WR Berkley have all filed to exclude AI from their policies.
We’re building three things:
1. ZKML-verified receipts - cryptographic proof of every action your agent takes. You can prove exactly what happened without exposing your model weights.
2. Real-time risk scoring - we watch how your agent behaves and adjust premiums dynamically. Safe agents = cheaper insurance.
3. Trust certificates - like SSL, but for AI agents. Your users can verify your agent is insured.
We’re two technical founders building the cryptographic verification layer for AI agents. Right now, Certus gives you receipts, risk scores, and trust certificates. Our roadmap leads to something bigger: making this the infrastructure that enables real liability coverage for autonomous AI.
We’d love your feedback on the SDK and the dashboard. What would you need to see before trusting an AI agent with high-stakes tasks?
Interactpitch
This looks super interesting.