Articles & notes

People are finding things through ChatGPT and Perplexity instead of Google. I built a pipeline that handles the optimization for that automatically — here's how it works.

At Zeta Global, my team gave me room to figure things out. I tried to do the same for the people who came after me — from responsive templates to training engineers across time zones.

I had 45 rule files telling my AI how to behave. The output was getting worse, not better. Then I measured — 170KB of context loaded per session. Here's what happened when I deleted half of them.

When I build with one AI for too long, the output starts drifting — confident but incomplete. A second model catches what the first one misses. Here's the two-pass process I use now.

I added Husky because of an anti-pattern. CI because of an anti-pattern. PR requirements because of an anti-pattern. None of it came from reading best practices. It came from breaking things and writing it down.