Blog on business websites, Google and AI
We write about what we see in other people’s audits and in our own deployments. Specific line items in a quote, specific traps in contracts, specific settings. Including when the conclusion is "you do not need this".
How to install a Claude skill. Upload a ZIP in the app, drop a folder in Claude Code
Installing a skill depends on where you work. In the Claude app you upload a ZIP file, in Claude Code you copy a folder or install a plugin. We walk through all three.
What is a Claude skill? A folder of instructions Claude reads only when it needs them
A skill is a folder with a SKILL.md file where you write a repeatable instruction once. Claude keeps only its name and description in view and reads the rest when a task matches.
Claude Cowork limits and safety. Files from your disk are processed on Anthropic's servers
How Cowork uses your limit, where your files go, what prompt injection is, which approval mode to choose and what not to give Claude Cowork.
Claude Cowork for office work. Five tasks with a ready instruction and what to check after
Receipts, scan names, meeting notes, a spreadsheet from several exports and a deck from notes. Five office tasks for Claude Cowork with an instruction you can copy.
Claude Cowork setup and first run. The Cowork button may already be gone
Which plans and systems Claude Cowork runs on, how to install Claude Desktop, connect a folder, set the approval mode, and what changed with the new view where chat and Cowork are one conversation.
Tokens and the context window. What they are and what takes up space before you type
What a token is, what an AI model's context window is, what fills it and what happens when it is full, in a chat, in the API and in Claude Code.
What is an LLM. The model predicts the next piece of text, it does not check facts
What a large language model is, how it is trained, why it makes things up with full confidence, and how a model differs from an app like Claude or ChatGPT.
AGENTS.md vs CLAUDE.md. Claude Code reads AGENTS.md on its own until you add a CLAUDE.md
How AGENTS.md and CLAUDE.md differ, when Claude Code reads AGENTS.md with no help, and how to keep one source of rules for every coding agent.
What is AGENTS.md. A Markdown file with no required fields that Codex, Cursor and Copilot read
AGENTS.md is a README for AI coding agents. What to put in it, where it goes, how nested files work and which tools read it.
Terminal, VS Code or Antigravity. Which to pick for Claude Code when you code a little or a lot
Claude Code is one engine with several ways in. When the terminal is enough, when the VS Code panel is better, and when you do not need Claude Code at all, only the Antigravity agent.
Claude Code in Google Antigravity. What surely works and what Anthropic does not confirm
Does Claude Code work in Google Antigravity. The terminal does, the extension is unconfirmed, and Claude models in Google's agent are not Claude Code. How to check it yourself.
Claude Code in VS Code. The extension that shows changes next to your code before you accept them
How to install the Claude Code extension in VS Code, how the panel differs from the terminal, which settings are shared and whether it works in Cursor and other editors.