The Demo Worked Great. The Deployment Did Not. Every few weeks, a new AI agent demo drops and the timeline lights up. Someone ships a polished video, the agent breezes through a 12-step workflow in 90 seconds, and the replies fill with “this changes everything.” I get it. The demos are genuinely impressive sometimes. Then…
CLAUDE.md Is the Most Underrated File in Your Codebase I’ve spent a lot of time tuning prompts. System prompts, user prompts, few-shot examples, all of it. And I’ll tell you what most of that work produces: marginally better output that degrades the moment the conversation gets long or the task gets complicated. So when something…
Why Your Second Brain Is a Graveyard (And How to Fix It) Most engineers I know have built at least one elaborate knowledge system. Notion workspace with nested databases. An Obsidian vault with backlinks going nowhere. A bookmark folder containing 400 links they will never read again. They spent a weekend setting it up, felt…
Claude in Microsoft 365: Context Persistence Is the Feature That Actually Changes Work Most AI integrations into enterprise software follow a predictable pattern. A model gets bolted onto a sidebar. It answers questions about the document you have open. You close the document, and the AI forgets everything. You start fresh every single time. That’s…
One Guy, One MacBook, $18,800 a Month I have seen a lot of “AI agency” pitches in the past two years. Most of them are courses dressed up as case studies. This one is different. A solo operator, no employees, no office, no sales team, is pulling $18,800 a month selling websites to local businesses….
The 100-Agent Problem Nobody Wants to Talk About Boris Cherny, the creator of Claude Code, said something at a recent Sequoia AI session that stopped me mid-scroll. “100% of my code is written by Claude Code. I run around 100 agents at one time.” He’s an Anthropic engineer reportedly compensated at $750K per year. He…
Anthropic Just Published an Operational Manual for the Agent-First Company I’ve read a lot of AI research papers, product announcements, and thought leadership posts over the past few years. Most of them describe a future. Anthropic’s Claude Code best practices document describes a present. That distinction matters more than people are giving it credit for….
Anthropic and Open Source: Reading Between the Lines on a Very Big Rumor Something is shifting at Anthropic, and the AI community is paying attention. A short video clip circulating on X shows Dario Amodei apparently reacting to a post about open-source AI winning. The original tweet from Ahmad (@TheAhmadOsman) reads simply: “Contrary to the…
LLM Evals Are an Engineering Discipline. Start Treating Them Like One. There’s a moment I’ve seen play out on too many AI teams. The demo works. The vibes are good. Someone says “ship it.” And everything is fine, right up until it isn’t. Users hit edge cases nobody tested. Outputs drift. Trust erodes fast and…
Anthropic Just Released a Free Prompting Workshop. Pay Attention. Most prompting advice you find online was written by people who poked at a model until something worked, then published it. Some of that advice is genuinely useful. A lot of it is pattern-matching dressed up as insight. When Anthropic’s own team releases a 24-minute workshop…
