AI agents & architecture
What separates agents from workflows, how much to trust them, and how to govern them.
Engineering Leader · Salesforce Architect · Enterprise AI
I've spent more than a decade building enterprise software, mostly on Salesforce. Now I write about what it takes to make AI work inside those systems: the architecture, the tradeoffs, and what breaks after the demo.
Featured essay
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.
Read essay →

Projects
Takes an architecture decision from open question to sourced recommendation and written record, and nothing gets saved until a person approves it.
TypeScript · Mastra · OpenAI · Pinecone · Streamlit
Ask your architecture docs a question and get an answer you can check, with sources, or a plain "I don't know" instead of a confident guess.
TypeScript · Mastra · OpenAI · Pinecone · Streamlit
What I write about
What separates agents from workflows, how much to trust them, and how to govern them.
Why AI projects stall on data and trust, and how to tell real returns from stage demos.
Agentforce, integrations, and platform architecture, from the point of view of the teams who run them.
Technical decisions, system design, team leadership, and building software that remains reliable at scale.
Working on enterprise AI or Salesforce? Let's discuss.