Perspectives

Weekly writing on AI strategy, architecture, and the real challenges of making AI work at enterprise scale.

All views expressed here are my own and do not represent the views of my employer.

Governance 10 min read May 2026

Earned Autonomy: How AI Agents Build Trust Over Time

The most dangerous thing you can do with an AI agent is trust it too quickly. Here's the case for graduated autonomy - and why the rules for gaining and losing trust should be deliberately asymmetric.

Architecture 10 min read May 2026

When Your Agents Should Disagree

Most multi-agent systems treat disagreement as a bug. The best ones treat it as signal. Here's why deliberately biased agents produce better collective decisions.

Architecture 12 min read May 2026

Beyond Orchestrators: The Architecture Patterns That Will Define Next-Generation Agent Systems

The orchestrator model is hitting its ceiling. Here are the architectural patterns emerging to replace it — and why financial markets might be the proving ground.

Protocols 10 min read April 2026

The Missing Protocol: Why Multi-Agent AI Needs a Consensus Standard

MCP handles tools. A2A handles discovery. Nobody has solved how agents actually agree on what to do. Here's what that protocol would look like.

Agentic Systems 8 min read April 2026

Why Most Agentic AI Projects Will Fail — And What the Survivors Will Look Like

Gartner predicts 40% of agentic AI projects will be cancelled by 2027. From what I'm seeing on the ground, that number might be generous.

Architecture 7 min read April 2026

The Agent Marketplace Problem: Why Governance Is the New Platform Play

When every team is building agents in silos with different frameworks, you don't have an AI strategy. You have technical debt with a chatbot interface.

Strategy 6 min read April 2026

Data Quality Is Still the Boring Problem That Kills Exciting AI Projects

Everyone wants to talk about models. Nobody wants to talk about the data feeding them. Twenty years in, and this hasn't changed.