Writing
Essays & notes
AI systems & architecture
18 min readYou Can't Secure Agents You Can't Find: A Practical Guide to AI Agent Discovery and Governance
Discovery is just the first layer. A five-layer framework — discovery, identity, authorization, observability, enforcement — for governing AI agents, and how Microsoft, AWS, Salesforce, and security vendors each cover only part of it.
AI systems & architecture
4 min readThe Hardest Part of Enterprise AI Isn't the Model — It's the Data
Enterprise AI projects rarely fail because the model isn't good enough. They fail because nobody trusted what it was reading.
Salesforce & Agentforce
7 min readDreamforce 2026: The Agentic Enterprise Meets Its ROI Reckoning
Salesforce's agentic enterprise pitch is compelling on stage. Whether it's compelling on a purchase order is the story that actually matters this year.
AI systems & architecture
8 min readHow Much Should You Trust an AI Agent?
Agent autonomy shouldn't be all or nothing. It should depend on the risk of being wrong.
AI systems & architecture
4 min readAI Agents vs. Workflows: Not Everything With an LLM Is an AI Agent
Why sending an email after answering a question doesn't make an LLM an AI agent — and how to actually tell workflows and agents apart.