building
Added the notes distribution layer
Notes now have a clear cross-post path for LinkedIn and X, plus copyable post text. The goal is simple: publish once on the site, then drive attention back to the owned page.
Notes
Clear notes: core ideas, insights, and useful takeaways from what I’m reading and studying.
Build in public
Notes that show the work as it ships
Every note can be cross-posted to LinkedIn or X, but the canonical link lives here. The point is to turn lessons, launches, and technical decisions into public proof.
shipped
Added demo media slots to product pages
ResistGate and Amethyst now have explicit demo sections using real screenshots, with room to replace them later with GIFs or recorded walkthroughs.
writing
Published 3 pillar posts on AI engineering
Wrote three long-form pieces targeting the gaps I see in production AI work: reliable product design, agent architecture patterns, and prompt engineering for real inputs. These are the things I keep explaining to people. Now they are linkable.
Product thinking
Product thinking
Building Product Revenue Funnels in Public
A product page is not proof by itself. The funnel needs visible outcomes, demo evidence, and a reason to stay connected.
I am turning the portfolio into a compounding product system: clearer product pages, demo media, email capture, and build notes that show the work as it ships.
April 25, 2026
Product thinking
Legacy UI is the New Tech Debt
An API can handle the whole thing.
Most businesses still expect people to navigate web pages and click buttons when an API could handle the whole thing. It's time to move towards raw APIs and CLIs.
March 14, 2026
Product thinking
Personal Page - From Portfolio to Product
Stop presenting projects. Start shipping a system that compounds trust.
A personal site should operate like a product: clear positioning, one CTA, proof, distribution, and legal foundations that make growth and revenue sustainable.
February 26, 2026
AI engineering
AI engineering
How to Build Reliable AI Products: A Production Engineering Guide
Reliability is an engineering discipline, not a model property.
Most AI products fail in production not because the model is wrong, but because the engineering around it wasn't built for variance. Here's the framework I use.
April 20, 2026
AI engineering
AI Agent Architecture: Patterns That Actually Work in Production
Agents fail at the seams, not the steps.
Most agent architectures break not because individual steps fail, but because the connections between them weren't designed to handle failure, ambiguity, and partial state.
April 17, 2026
AI engineering
Prompt Engineering for Production: Moving Beyond Demos
Prompts that work in demos fail in production because demos don't have variance.
Demo prompts are optimized for the best case. Production prompts need to handle the full distribution of real inputs. That requires a different design philosophy.
April 14, 2026
AI engineering
AI builders: chase primitives, not model size
Models impress. Systems ship.
Bigger models are not the same as better products. Real progress comes from primitives and engineering patterns that reduce variance and make outcomes reliable.
February 26, 2026
Systems design
Founder mindset
Mindset
Performance
Building in public
Follow the journey
as I build AI tools, products, and a serious founder life.
No spam. Unsubscribe anytime.