
Putting GA4 where the work happens: an in-browser analytics overlay and its MCP bridge
Content teams shouldn't have to leave the page to learn how it performs, and neither should AI agents.
I ship systems that deliver impact. I understand technology and human organizational dynamics equally — and how to make them work together. Twenty years with UN agencies, international science, and media have sharpened that.

Content teams shouldn't have to leave the page to learn how it performs, and neither should AI agents.

Cultivating LLM productivity requires comfort with the vernacular of code, not the writing of it.
EmDash doesn't need to win to matter, and Drupal's quiet modernization work means it doesn't either.
Tips on where the shared appproach doesn't share, and plugin.json gotchas that break Claude Code silently.

Several traditions solved the shared-understanding problem in parallel. LLMs are dissolving the boundary that kept them apart.

Developers are moving from copy-paste to orchestration. Each gear shifts what the human actually contributes.
The skeleton loading problem is a contract problem in disguise; explicit content schemas dissolve it.

AI has general knowledge of the universe, not yours. The engineers who get results were always doing context work.
Software engineering is splitting into tiers, and in every tier the remaining human work is holding context.
AI-generated code is outpacing human understanding — and teams need to self-govern before someone else does.
Open to strategic opportunities — let’s connect.
Printed direct from AllAboutKen.com