For years my "portfolio" was a folder of screenshots and a LinkedIn profile. Every time I sat down to build something better, I got stuck in the same place: the tools were either too rigid (drag-and-drop builders) or too technical (learn to code first, market yourself later).
This time I tried something different. I rebuilt the whole thing as a proper website - and I let an AI coding agent, Claude Code, do the engineering while I stayed in the seat I actually know: the marketer.
What I did, and what the AI did
I made the decisions. The AI did the building.
- I owned the strategy and copy - what to show, the order, the wording, the positioning.
- The AI owned the code - the layout, the responsive design, the deployment, the before/after slider, the analytics setup.
- We iterated in plain English. "Group my experience by employer." "Make this a before/after slider." "Move that section to a new page." No tickets, no waiting.
The result is the site you're reading this on - and it went live the same week.
Why this matters for marketers
The lesson isn't "everyone should code." It's that the gap between an idea and a shipped thing is collapsing, and marketers who learn to direct AI well will move much faster than those who wait for a queue.
The skill isn't prompting. It's knowing what good looks like, and being able to describe it clearly.
That's a marketing skill, not a technical one. Briefing an AI agent is a lot like briefing a designer or a developer: be specific, give examples, react to what comes back, and keep the standard high.
What I'm writing about here
This blog is where I'll share the practical side of AI for marketing - the workflows I actually use, not the hype:
- Using AI in email and CRM (segmentation, A/B tests, first drafts)
- Speeding up content and SEO without losing the human voice
- Building small automations that save hours every week
If any of that is useful to you, stick around - more soon.