Field notes
Practical notes on AI products, CTO decisions, and the platforms that keep them reliable.
Latest field note
A practical framework for deciding which parts of an AI product should be custom, bought from a vendor or assembled around proven services.
Read the articleA compelling AI demo proves a possibility. Production software must also be secure, observable, affordable and dependable when reality arrives.
AI has made code faster to produce, but dependable software still requires product judgement, verification and operational ownership.
AMPD and CarBuddy AI sit at different points in the customer journey, but they keep teaching the same lesson: the hard part is not…
If you’re not a programmer but want to harness the power of AI to build software, create websites, or automate tasks, the landscape of…
There’s a special place in my heart for those five words. Right next to “the build works on my machine” and “we’ll document it…
Lovable (formerly GPT Engineer) is brilliant for getting your startup from idea to MVP at lightning speed. You can ship a working product in…
Why I Chose Cal.com Over Calendly for My DevOps Consultancy As an indie founder building AlanOps, I needed a booking system that felt professional…
🧠 Watch the original video by IndyDevDan Over the past few months, I’ve been experimenting heavily with agentic coding — building systems where AI…
A comprehensive guide to maximizing productivity with Claude Code based on proven community strategies and best practices. Table of Contents Foundation: The CLAUDE.md System…
Working on something difficult?
