•AI
The HTTP/HTTPS Debugging Nightmare: A 24-Hour Journey Through Mixed Content Hell
I spent 24 hours debugging why my React app kept making HTTP requests from HTTPS pages—even though my code was converting them. The culprit shocked me.
Blog
486 posts about AI, learning, and building products
•AI
4 Weeks in: Building a 10-Agent Marketing Platform While Taking Naps
I built 3 AI marketing agents with multi-tenant architecture in 4 weeks—the same amount I accomplished in a month building my previous product that took 7 months to launch.
•AI
Safer Deployments for Solo Devs: How I Used AI to Ship (a Feature Flag Story)
I almost shipped a major TTS engine swap by just "hoping for the best"—until my AI assistants flagged the risks and helped me build a bulletproof feature flag strategy instead.
•AI
From 3 Minutes to 500ms: The Signup Bug That Made No Sense
I hunted down a 3-minute signup delay that turned out to be Schrödinger's user—existing and not existing at the same time due to database replication lag between writes and reads.
•AI
Your AI Ghostwriter is a Bad Idea. Here's How to Use an AI 'Thought Partner' Instead
I rebuilt my AI tool after watching it confidently spout wrong information about my own expertise—here's the 4-step workflow that puts you in control instead.
•AI
One AI Parameter Change Cost Me $54/Month
I thought my Cloud Run migration was flawless until a single AI parameter—temperature set to 0.7 instead of 0—caused 30% failed API calls and cost me $54/month in wasted tokens.
•AI
From Advertising to Engineering: Technical Lessons from Building DIALØGUE
I migrated from AWS to GCP and achieved 92% cost reduction with 10x faster performance—here's what I learned ditching "best practices" for pragmatic architecture that actually works.
•AI
DIALØGUE: Building an AI-Powered Podcast Generator from Scratch (And Learning a Ton Along the Way)
I built an AI podcast generator that lets you shape the content before it's created—because I was tired of AI just reading Wikipedia at me during my commute.
•AI
Google Gemini 2.5 Pro is now my go-to coding partner
After 5,000 hours testing AI models, Gemini 2.5 Pro beats Claude and ChatGPT for coding—here's why it became my default tool for building complex applications.
•Driving in the US
Four Utah National Parks in Winter: A Red Rock Journey
Winter transforms Utah's red rocks into something magical—we discovered snow-dusted arches, empty scenic roads, and a sense of community that rivals the landscape itself.
•AI
CrewAI is Good! - My First Impressions
After 10 days building AI-generated podcasts with CrewAI, I learned that while the framework is remarkably easy to use, quality content still demands real human effort.
•AI
I Cheated: Sydney Can Now Read the Narrative in 10-K Reports
I scaled Sydney to read 10 years of narrative content from Big Tech's annual reports by strategically limiting scope to 7 companies—here's how I balanced cost vs capability.