What we write. What we read. What we give away.
Short notes from the field, long-form guides you can run this week, and the outside sources we actually trust.
Latest notes
From the blog
- Fundamentals·Apr 9, 2026
Model vs harness vs environment
The mental model that separates three different problems people keep conflating when they talk about agents.
- AI·Apr 6, 2026
Reading release notes so you don't have to: Opus 4.6 week
What actually changed in Opus 4.6, what it means for agent builders, and what we changed in production the same day.
- Industry·Apr 2, 2026
Why we built our own agent harness
Eight months of iteration on a custom harness, what it buys us over off-the-shelf, and where we still use vendor tools.
Guides
Playbooks you can run this week
Recommended reading
What Alex actually reads
A short list we revisit. Primary sources over commentary, practitioners over pundits.
Anthropic Engineering
How the people building Claude think about prompt caching, tool use, and agent evaluation.
OpenAI Research
Primary source on model capabilities, safety research, and benchmark releases.
Google DeepMind Blog
Frontier research writeups that rarely make it into vendor marketing summaries.
Simon Willison's Weblog
Daily, skeptical, hands-on coverage of LLM releases with runnable examples.
Interconnects by Nathan Lambert
Research-grade analysis of the open-source model ecosystem and what the numbers actually mean.
Model Context Protocol docs
The spec we build against when we stand up agent tool surfaces for clients.
Rather skip the reading?
Thirty-minute working call. We walk through what fits your situation and leave you with a plan.