Practice
AI in Operations & Marketing
“I'm not an AI researcher. I'm an operator who builds with AI.”
The Philosophy
AI doesn't replace operators. It makes good operators dangerous.
The hype cycle around AI is exhausting. Every tool claiming to replace every function. Every LinkedIn post about prompts. Every consultant calling themselves an AI expert after two weeks with ChatGPT.
The reality is simpler and more interesting. AI is infrastructure, like electricity or the internet. The question isn't whether to use it — it's whether you understand it well enough to build with it, not just use the interfaces someone else built.
The difference between using AI tools and architecting AI systems is the difference between driving a car and designing one. Both are valuable. But only one of them lets you build what doesn't exist yet.
What I've Built
Proof of concept, in production
AgentReady.site
AI readiness scoring SaaS. Built to learn AI agent architecture hands-on — from API design to Claude MCP server integration.
AI-powered content engine
Automated content workflows for LinkedIn and multi-platform distribution. Built on Claude, not prompts.
Automated lead scoring
LLM-powered classification of inbound leads by intent, fit, and timing. Reduces response time from hours to seconds.
Financial tracking workflows
AI-assisted extraction and categorisation of financial data from unstructured sources. No more manual spreadsheet work.
Tools I Work With
- Claude (Anthropic) — primary reasoning layer
- MCP server architecture — tool integration
- Vercel — deployment and edge functions
- Next.js — application framework
- Ahrefs — SEO data integration
Interested in how AI applies to your operations? Let's talk.