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
The Prompt Engineering Myth: 7 Problems Breaking EU AI Startups in 2026
Stop optimizing prompts. Discover the 7 architectural flaws breaking EU AI startups in 2026 and the Sovereign Workflow roadmap for compliant, scalable AI.
How to Build a Production LLM Observability Stack in 2026
A practitioner's guide to the winning stack: Tracing (Langfuse), Cost Control (LiteLLM), and Governance (PromptMetrics). Includes a Week 1 to Quarter 1 implementation plan.
The 4 AI Loops of Death That Kill EU Startups Before Series A
Spending €2k–€50k/month on LLMs? Discover the 4 hidden loops destroying startup margins and compliance readiness, and the 90-day plan to fix them before the EU AI Act hits.
LLM Behavioral Drift: Why Your Observability Stack Fails the EU AI Act
Is your LLM drifting into sycophancy? Discover the "hidden personality" risks exposed by 2026 research and how to meet Article 9 monitoring requirements.
Why Your LLM App Breaks at Scale: 7 Architecture Mistakes (2026)
Is your LLM bill eating your runway? Discover the 7 critical architecture mistakes killing AI startups in 2026 and the production-ready stack to fix them, from semantic caching to EU AI Act compliance.
What the Remote Labor Index Proves About Your AI Mandate
AI agents automate 15.8% of real freelance work, up from 2.5% a year ago, and still fail most jobs. Here's what that means for your AI mandate
The EU AI Act Compliance Crisis: 5 Misconceptions Putting Startups at Risk
48% of AI startups aren't ready for the EU AI Act. Discover the 5 compliance myths risking your runway, from the "low-risk" trap to the August 2026 deadline.
Open Source vs. Enterprise LLM Observability: The EU CTO’s Guide
EU CTOs: Why your "free" open source LLM observability setup could cost €200K in hidden compliance expenses. A practical TCO guide for the AI Act era.
The High Cost of Silent AI Updates: Preventing $10k Weekends
From schema drift to runaway cost loops, silent model updates are a liability. Here is how defensive engineering and "Golden Sets" protect your enterprise AI.
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.