Writing about AI agents, engineering, product ideas, and lessons learned building tech products. From practical implementation guides to big-picture thinking.
8 articles.
Why agentic automation is gaining ground: flexibility (update briefs, not code), compounding gains from better models, and systems that learn from feedback instead of fixed rules.
There are different types of automations, and the approach matters more than most people realise.
Most teams use AI; few get impact. Lessons from two years building agents on what actually works: connect real context, design agentic flows, and keep humans in the loop.
There are two universal truths agencies (and everyone else) have to accept in order to survive: Everything that can be automated should be, but not everything can be automated
Chat was how GenAI went mainstream. Here’s what it’s good at, where it breaks, and why it’ll stick around until we invent better interfaces.
Procurement, data, models and margins: why Google is positioned to ‘win’ AI in advertising as the model other builders use.
LLMs are not as good as some say, but not as bad as others do. They’re inconsistent, by design.
How building memory into AI Agents makes them smarter, more consistent and more reliable.
I love talking about AI, building products, and solving interesting problems. Reach out if any of these topics resonate.