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 95% Accuracy Trap: Why Multi-Step AI Agents Fail
A 95% per-step accuracy means your 10-step AI agent fails 40% of the time. Discover the math behind cascading errors and how to fix agent reliability.
Your RAG System Is Silently Failing: Why Traditional Metrics Miss It
Is your RAG system returning "200 OK" but hallucinating? Learn why traditional metrics fail to catch silent degradation and how to monitor drift in production.
LLM Vendor Lock-in: Why Switching Costs 10x More Than You Think
Most teams underestimate LLM switching costs by 3x. The issue isn't the API, it's prompt lock-in. Learn how to build a multi-provider strategy that works.
Claude Code Agent Teams vs. Subagents: Is the 7x Token Cost Worth It?
Is Claude Code Agent Teams worth the 3-7x premium? We compare Agent Teams, subagents, OpenClaw, and LangGraph to help you balance AI velocity vs. budget.
Why Your US-Built AI Observability Tool Can't Answer EU Auditor Questions
Is your AI stack compliant with GDPR and the EU AI Act? Most US observability tools fail on data residency and deletion. Here are the 5 gaps you need to close.
Your AI Agent Can't Explain Itself: Why LLM Observability Fails EU AI Act Compliance
Most AI agents fail Article 12 audit. Learn why standard observability isn't enough for EU compliance and how to build audit-ready traces for LangChain & CrewAI
Do You Actually Need LLM Observability? An Honest Review (2026)
An honest, transparent review of LLM observability for 2026. We analyze the ROI, EU AI Act compliance risks, and tell you exactly when you don't need a tool like PromptMetrics.
The gate is your hallucination detector
GPT-4 scored zero hallucinations on a major benchmark. Re-annotation found 83. Here's how operators catch confident errors without an ML team: the review gate.
Your Prompts Are Broken: A CTO’s Guide to Production Prompt Engineering
Stop treating prompts like conversation. Learn the 5 engineering techniques to fix prompt drift, cut LLM costs, and secure AI agents against indirect injection.
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.