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
LLM Wiki: The Self-Writing Knowledge Base Your Claude Code Setup is Missing
Developers spend 64% of their day searching for answers they already have somewhere. Karpathy's LLM Wiki pattern slashes that by building a...
The AI Builder's Guide to Building Skills for Claude Code
This guide covers building custom SKILL.md files from first principles to multi-skill architecture, with essential security patterns.
ReAct Loops vs Deterministic Orchestration for AI Agents
Prompt Engineering is Dead: The 2026 LLM Orchestration Playbook
Prompt engineering is deprecated at scale. Discover the 2026 LLM orchestration and prompt governance playbook for EU CTOs to scale AI securely and compliantly.
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.
Single-Agent vs. Multi-Agent AI: A CTO’s Guide to Architecture & Costs
Is your multi-agent system burning tokens? Discover the "Coordination Tax" hidden in agentic AI. We compare Single-Agent vs. Multi-Agent architectures on cost, reliability, and speed to help you build production-ready systems.
Production-Grade Semantic Routing: A CTO’s Guide to AI Gateways
Cut LLM costs 40–60% with semantic routing. A technical guide to multi-tier AI gateways, cascading logic, and policy-as-code governance for production.
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.