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.
Agents Speak Intent, Not Implementation
MCP secures the pipe. It doesn’t govern the action.
The Model Context Protocol standardizes how agents discover and call tools. It says nothing about whether a given call should be allowed — and that question is the whole game.
Agents Speak Intent, Not Implementation
Agents Should Speak Intent, Not API
Every team building agents eventually rediscovers the same lesson: making the agent learn each provider's API turns out to be the wrong abstraction. The right one looks more like a verb.
Field notes on the agentic enterprise.
No noise. A few times a month, when there's something worth saying.