I built a protocol so AI agents can't just say 'trust me'

A few months ago I was wiring up a multi-agent pipeline where one agent writes code, another reviews it, and a third deploys it. Everything worked great in the demo.

Then I asked a simple question: if the review agent says "looks good," how do I actually know it ran the tests?

I couldn't answer it. Neither could MCP, A2A, or any framework I looked at.

The gap nobody talks about

MCP connects agents to tools. A2A connects agents to agents. These solve connectivity. But connectivity isn't accountability.

I built a protocol so AI agents can't just say 'trust me'

Related reading

When AI Agents Ship Code: A Protocol for Verifiable Execution

When an AI agent says 'I ran the tests and they passed' — do you trust it?

How to prove what your AI agent actually did (to someone who doesn't trust you)

Proof launches x401, an open protocol for verifying who's actually behind AI…

I built a cryptographic passport for AI agents — here's how it works

How Do You Trust an AI Agent With Your Money? You Don't — You Check Its Receipt