All posts
Topic
Agents Speak Intent, Not Implementation
The safest thing an agent can know about your systems is almost nothing. When agents declare what they want rather than how to do it, credentials, providers, and payloads stay on the governed side of the boundary. These pieces explore intent as the right interface between reasoning and execution.
Written for The Builder — Head of AI · Principal/Platform Engineer.
Field notes on the agentic enterprise.
No noise. A few times a month, when there's something worth saying.