profile

WotAI

If you're building with Claude Code, n8n, or AI agents in production, this is the email I'd want. Weekly recap of what shipped, what broke, and how I'm running it. Specific over vague. Replies welcome.

Featured Post

AGENTS.md vs CLAUDE.md, tested on 13 repos

AGENTS.md vs CLAUDE.md, tested on 13 repos 12 of mine load it. One never did, and I didn't notice for a month. AGENTS.md vs CLAUDE.md, tested on 13 repos Hey there, I have 13 repos that carry both an AGENTS.md and a CLAUDE.md. This week I checked how each one wires them together, expecting 13 identical answers. Twelve import AGENTS.md on line one of CLAUDE.md. One asks the agent, in a sentence, to please go read it. That one holds 6,479 bytes of branch rules and load-bearing invariants that...

This Claude Code plugin loads before you type

This Claude Code plugin loads before you type It installs itself into every session, then quietly wins six skills. Plus 2 more reads. This Claude Code plugin loads before you type Hey there, I have both of the big Claude Code process plugins installed in the same repo. It took me a while to notice that six of their skills do the exact same job. Nobody warns you about that, and the thing that decides which one wins is smaller than you would expect. Six Claude Code skills collide, and one hook...

Claude Code edited my video

Claude Code edited my video I never opened the timeline once, and the spec became the whole job. Plus 2 more reads. Claude Code edited my video Hey Reader, Three reads this week, and two of them are about the same quiet shift: the tool got good enough that the bottleneck moved somewhere less glamorous. An agent that can drive a video timeline still cannot decide what belongs on it. A workflow that looks automatable can still be the wrong one to touch first. I let Claude Code edit a video, and...

The viral Claude prompt, tested four times

The viral Claude prompt, tested four times Four documented runs, and the one check that decides all of them. Plus 2 more reads. The viral Claude prompt, tested four times Hey Reader, Three reads this week, and each one turns on the same distinction: a document that describes a standard, and a standard that something can actually be checked against. A prompt half the internet copied without the two parts that make it work. A config field nothing read at runtime. A voice guide every competitor...

Your CLAUDE.md File Is Too Long

1,204 lines down to 151 The four-bucket diet, and the 20 lines no model can rediscover. Plus 3 more reads. 1,204 lines down to 151 Hey Reader, Four reads this week, and each one spends its best section on the same question: which part of this should you leave alone? The lines you don't delete. The invoices you keep typing by hand. The decisions you never route through software. Every line gets paid for on every session (most don't earn it) Anthropic cut roughly 80 percent of Claude Code's own...

When not to buy an AI agent The three questions that decide it, and what a missed call is actually worth. Plus 3 more reads. When not to buy an AI agent Hey Reader, Two people in your business describe the same process differently. That is the clearest signal it is not ready to automate. You do not have a workflow, you have two workflows and a disagreement. Automate it anyway and you lock in whichever version the person configuring it happened to believe. This week's first two reads are about...

110 free AI models, tested 16 providers, what's actually free, and the catches each one hides. Plus 3 more reads. 110 free AI models, tested Hey Reader, Four reads this week. The first two go together: where the free AI models actually are, and how to put Claude Code in charge of them. 110 free AI models, and what each one actually costs you Sixteen providers hand out real API access right now. Not trials. Free tiers, running today. The catch is that "free" is doing different work at each...

The most powerful AI model lasted three days

The most powerful AI model lasted three days What it means for your business – and the one move that kept some teams calm. Plus 2 more reads. The most powerful AI model lasted three days Hey Reader, Anthropic shipped its most powerful model in years on June 9. Three days later, the US government pulled it offline – for everyone. If you run a business on AI, the story to take away isn't the politics. It's the quiet lesson it handed every operator about how to set up your stack. Anthropic's...

Open Design, running in 10 minutes The full setup on Claude Code, plus the #1 install gotcha. And 2 more reads. Open Design, running in 10 minutes Hey Reader, Open Design auto-detects 16 coding-agent CLIs and lets you swap engines with one click. The hard part is getting it running the first time. This week opens with the 10-minute setup on Claude Code, plus two more reads behind it. Open Design, running on your machine in 10 minutes Open Design runs locally with Claude Code as the engine:...

The Opus 4.8 number nobody's posting

The Opus 4.8 number nobody's posting Not the coding score. Plus Open Design at 4 weeks, and 2 more reads. The Opus 4.8 number nobody's posting Hey Reader, Anthropic shipped Claude Opus 4.8 this week, and the whole feed posted the same screenshot – the coding score. That's the least interesting part. The number that actually changes how you work is below, plus three more reads stacked behind it. Claude Opus 4.8 – the number nobody's posting Everyone screenshotted the coding score (64.3% to...