Back to Portfolio

Research

Runtimes, protocols and systems for AI agents

Whitepapers, open architecture and reference implementations, and research writing on AI-agent execution, identity, security and distributed coordination.

Featured research

White PaperVersion 1.2 · August 2026

Outcome Coordination for AI Agents

A technical architecture for governing execution within individual systems while coordinating outcomes across trust boundaries through explicit objectives, offers, commitments, evidence and settlement.

Read the paper Download PDF

Whitepapers

View all whitepapers

AI Agent Architecture · August 2026 · Version 1.2

Outcome Coordination for AI Agents

Governing execution within systems and commitments across trust boundaries

Authentication & Security · March 2024

RealTimeAuth (RTA): Dynamic Authentication

A superior alternative to OAuth for AI agents and modern applications.

Open architecture and reference implementations

Open-source runtimes, protocols and tools I use to test these ideas in working code.

Research writing

All articles

Lost in Execution — Your AI Agent Will Eventually Do Something You Never Asked For

How approved tools, valid credentials and correctly functioning systems can still produce an effect the user never authorised — from PocketOS to OpenAI's ExploitGym.

Dynamic AI Agents Orchestration

Why agent systems would move beyond static tool registries towards generated code and secure execution environments.

Why Code Execution Is Eating Tool Registries

How tool definitions, intermediate results and orchestration logic consume context and weaken control as systems grow.

The Missing Runtime Between AI Agents and Enterprise Backends

Why enterprise workflows need deterministic execution, durable state and policy outside the model loop.