Chief Platform Officer @ Opaque Systems

Building the Future of
Autonomous AI Systems

Agentic AI Architect • Engineering Leader • Scale by Subtraction Pioneer

I design production-ready AI agent systems that are reliable, governed, and truly autonomous—not just sophisticated chatbots. My work focuses on Control Planes, Deterministic Graphs, and the radical idea that systems scale better by removing complexity.

Explore My Work Read My Articles
4,877
GitHub Stars
microsoft/agent-governance-toolkit
10/10
OWASP Agentic Top 10
covered by AGT
5
Language SDKs
Python · TypeScript · .NET · Rust · Go
18
Years at Microsoft
before joining Opaque

Current work — open standards for trusted agents

TRACE cMCP Agent Manifest cA2A Agent Governance Toolkit

agentrust-io · hardware-attested governance for autonomous AI agents

🧠 Philosophy

Scale by Subtraction

The next generation of AI scaling won't come from adding more tokens—it comes from removing complexity.

🏗️

Control Planes over Prompts

We don't ask microservices "nicely" to respect rate limits; we enforce it. Why treat AI agents differently? Build the Kernel for the AI OS.

🕸️

Graphs over Context

Don't detect hallucinations after generation—prevent them structurally with multi-dimensional Knowledge Graphs that define what's possible.

🔇

Silent Swarms over Chat

Language is for humans. Code is for machines. The best agents are the ones that can't talk—they communicate through structured data.

🚀 Featured Work

Production-Ready AI Infrastructure

Open source projects that make autonomous AI systems reliable, governed, and actually useful.

🏛️
992 conformance tests ⭐ Flagship

Agent Governance Toolkit

The unified governance platform for AI agents, hosted under Microsoft. 5 top-level distributions, 5 language SDKs, ~10 framework integrations. 10/10 OWASP Agentic Top 10, NIST AI RMF alignment, OpenSSF best practices.

Python TypeScript .NET Rust Go
⭐ 4,877 on GitHub · MIT
🧾
agentrust-io

TRACE

Trust Runtime Attestation and Compliance Evidence. An open standard for hardware-attested trust records a verifier can check without trusting the operator.

Attestation Open Standard Compliance
📦 pip install agentrust-trace
🔐
agentrust-io

cMCP

Confidential MCP gateway. Enforces Model Context Protocol tool-call policy inside a hardware TEE, with the Cedar policy bundle measured into the attestation report and a signed proof per session.

MCP TEE Cedar Policy
🌐 cmcp.agentrust-io.com
🪪
agentrust-io

Agent Manifest

A cryptographic identity and provenance standard for AI agents. Hardware-anchors the artifacts that define an agent at deployment, so what is running can be proven, not just claimed.

Identity Provenance Python · TS
📦 pip install agent-manifest
🤝
agentrust-io

cA2A

Confidential agent-to-agent. Attested, attenuated delegation and sealed peer channels as a profile on the A2A protocol.

A2A Delegation TEE
🔗 github.com/agentrust-io/ca2a
🔬
Research

Scale by Subtraction

My methodology for building reliable AI systems. Focus on removing complexity rather than adding features. Via Negativa applied to software architecture.

Methodology AI Safety Architecture
📝
Writing

Technical Articles

Deep dives into agentic systems, architectural patterns, and the philosophy of building AI that works. Published on Medium and Dev.to.

Medium Dev.to LinkedIn
View All Projects →
🌐 Standards & Community

Shaping Agent Governance Standards

Contributing to the frameworks that will define how autonomous AI systems are built and governed.

🏛️

OASIS Open

Contributing to agent interoperability standards through the OASIS Agent Interoperability Technical Committee.

Agent Interop TC
📐

NIST AI RMF

AGT aligns with NIST AI Risk Management Framework profiles for responsible AI deployment in enterprise settings.

AI Risk Management
🤝

CoSAI / AAIF

Participating in the Coalition for Secure AI and the AI Agent Infrastructure Foundation to advance agent safety.

AI Safety
🛡️

OpenSSF

AGT follows OpenSSF best practices for supply chain security, dependency management, and vulnerability disclosure.

Supply Chain Security
✍️ Writings

The "Scale by Subtraction" Collection

Challenging conventional AI wisdom with practical, battle-tested approaches.

01

The Accumulation Paradox

"Sustainable agent architecture does not require agents that remember more; it requires agents that know how to forget."

Context Rot Agent Architecture Memory Hygiene
02

The Mute Agent

"Stop trying to prompt-engineer safety. Shift the burden of constraints from the probabilistic LLM to the deterministic Knowledge Graph."

Semantic Firewalls Zero Hallucination
03

The Agentic Architect Series

"We don't ask microservices 'nicely' to respect rate limits; we enforce it. Why are we treating AI agents differently?"

Control Planes Governance
Read All Articles →

Ready to Govern Your AI Agents?

Deterministic policy enforcement, tamper-evident audit trails, and trust-gated agent handoffs, all hardware-attested.

⭐ Star on GitHub Quick Start Guide
🔗 Connect

Let's Build the Future Together

Find me on these platforms for articles, code, and collaboration.

GitHub

Open source projects

LinkedIn

Thought leadership

Medium

Deep dive articles

Dev.to

Technical tutorials

X (Twitter)

Quick updates