I build the infrastructure that makes AI agents reliable, accountable, and cheap to run. My work sits at the intersection of cryptography, distributed systems, and large language models.
I'm the creator of the Q Protocol, an open coordination standard for multi-agent AI systems. It's running in production today on Google Cloud.
Q Protocol is an open coordination standard for multi-agent AI systems.
When AI agents need to work together, they normally communicate in
natural language, which is expensive (lots of tokens), slow, and
unreliable (agents can lie about what they did). Q Protocol replaces
that with short, structured coordinates like ◈ research:start:quantum.
Each coordinate is a point in a shared semantic space that all agents
understand without negotiating meaning every time. Every action produces
a cryptographic receipt that proves it happened. The result is a
multi-agent system that runs roughly 10x cheaper than natural-language
orchestration, with mathematically guaranteed integrity and a complete
audit trail of every decision.
The protocol is named Q after the compression objective that defines it: find the shortest coordinate message K that still produces correct execution. The goal is coordinate communication that approaches zero tokens, which the Q represents.
Three architectural guarantees make the system trustworthy at enterprise scale:
BLAKE3 cryptographic receipts prove every action. An orchestrator cannot claim execution without a verifiable receipt from the executing agent.
Mandatory state querying on every session. The runtime refuses to execute agents that skip Brain initialization. Architecturally enforced, not optional.
One universal runtime image deploys all agents. The goal isn't cheaper tokens. It's eliminating them.
The protocol's mathematical foundations are described in the paper "Q Protocol: Achieving K→0 Agent Coordination Through Shared Semantic Space," which formalizes coordinate-based communication, proves cross-model semantic convergence without shared weights, and presents the full production validation.
Cross-model convergence tested across Claude, Gemini, and GPT-4. Models with independent architectures converged to less than 2% semantic distance after 100 interaction cycles through shared coordinate space alone.
An Identity Cube is a machine-readable, cryptographically signed identity document. Instead of scraping HTML, AI agents and crawlers can parse a structured cube directly. This is a live example.
{
"@context": "https://a2ac.ai/identity/v1",
"cube_type": "identity",
"did": "did:cube:phil-hills-seattle",
"name": "Phil Hills",
"location": "Seattle, WA",
"role": "AI Systems Architect",
"org": {
"name": "A2AC LLC",
"url": "https://a2ac.ai"
},
"created": "Q Protocol",
"description": "Open coordination standard for AI agents. Agents point rather than talk.",
"capabilities": [
"agent-orchestration",
"protocol-design",
"cryptographic-identity",
"gcp-infrastructure",
"sdk-development"
],
"canonical": {
"website": "https://philhills.ai",
"github": "https://github.com/Phil-Hills",
"linkedin": "https://www.linkedin.com/in/philhills/"
},
"verification": {
"algorithm": "BLAKE3",
"hash": "computing..."
}
}
The Identity Cube spec is part of the Q Protocol. Any agent or human can publish one as a machine-readable identity document, verifiable via BLAKE3 hash. No HTML scraping. No inference. Just structured truth.
I'm open-sourcing the Q Protocol specification. If you're building multi-agent systems and want to stop paying for agents to talk to each other, let's connect.