Field notes.
Real opinions about what AI is getting right and wrong for operators in 2026, written by us, in our own voice, not a content calendar. Plus the occasional teardown of something Izzy built and what it taught us.
Articles
Top Problems With "Vibes-Based" Prompt Engineering & How to Fix Them
Is your AI strategy stuck in Prompt Dependency Hell? Discover the top 4 risks of vibes-based prompt engineering, from cost spikes to bugs, and how to switch to a reliable code-first approach.
Why Hardcoding Prompts in Git is a €10M Technical Debt Trap
Hardcoding prompts in Git hides LLM costs and creates compliance risks. Discover why this technical debt kills velocity and how to decouple prompts now.
7 EU AI Act Architecture Traps for SaaS CTOs (And How to Fix Them)
Is your SaaS architecture ready for the EU AI Act? Discover 7 hidden technical traps—from logging failures to risk classification—and the engineering fixes you need before 2026.
5 Critical LLM Prompt Management Mistakes EU Teams Make (2026 Guide)
Learn how EU AI teams avoid version control chaos, compliance gaps, and cost overruns. Includes Python code examples, EU AI Act checklists (Articles 11 & 12), and testing frameworks.
How Much Does LLM Observability & EU AI Act Compliance Really Cost?
How much does EU AI Act compliance cost? We compare build vs. buy, hidden fees, and show the ROI of an LLM observability platform to avoid €35M fines.
Field notes, in your inbox
One email per week. No content calendar — just what we’re building, what broke, and what we changed our minds about.
Operator Stack
The free community where we continue these conversations between posts.
Join free