Factnetize: tested AI, health and WordPress guides

Hands-on guides we test ourselves: AI agents and Claude, local AI on Windows, WordPress run with AI, and health claims checked against the studies. No ads, sources linked.

Illustration of a laptop on a dark navy desk connected by amber light lines to five task objects: a slide with a side panel, a folder with a chart, two quotes, a browser price tag, and an alarm clock

AI · Featured

Put Claude to work: PowerPoint, data, quotes, Chrome, and schedules

Five real tasks for Claude beyond the chat: change an open PowerPoint, analyze a folder of sales data, compare quotes in a project, compare prices with Claude in Chrome, and run a…

John Lock · November 7, 2026 · 7 min read

Read the full article

Claude Research: investigate a question and check sources

John Lock · November 7, 2026

Claude connectors: connect your tools and find information

John Lock · November 7, 2026

Where curiosity meets clarity — articles for the kind of mind that asks "but why?" three times in a row.

AI

View all articles

Claude Skills: turn a workflow into a reusable skill

A Claude skill stores a procedure you'd otherwise paste into every chat. Create one by describing it in a conversation, save it,…

John Lock · November 7, 2026

Claude artifacts: create docs, slides, and designs

Ask Claude for an artifact and you get the flyer, brief, or deck itself, not a paragraph of tips. Eight numbered steps:…

John Lock · November 7, 2026

Claude Projects: reusable context and clear instructions

A Claude project saves your brief and your rules once, so every new chat starts with them. Set one up for a…

John Lock · November 7, 2026

Agentic AI

Building, running, and understanding agentic AI — assistants and agents that plan, use tools, and act on their own.

View all articles

Agentic AI

Hermes vs Claude Code: which one for which job

Hermes and Claude Code both schedule tasks, run subagents and speak MCP. Five questions decide which fits your job, and you can…

John Lock · November 2, 2026

Agentic AI

When Claude hits its limit mid-task: continue in Hermes from one Git repo

When Claude hits its limit mid-task, Hermes can continue from the same private Git repo. Set up one rules file and a…

John Lock · November 2, 2026

Agentic AI

AGENTS.md vs CLAUDE.md: the difference, and which file your agent reads

AGENTS.md is the open instruction file most coding agents read; CLAUDE.md is Claude Code's own. Which file six agents read, when Claude…

John Lock · November 2, 2026

Health

View all articles

Health

Creatine for strength and muscle: what the trials show

Pooled trials show creatine adds a modest amount of lean mass and strength on top of resistance training, and plain monohydrate does…

Pablo Vicento · October 26, 2026

Health

Magnesium glycinate for sleep vs melatonin: what the evidence shows

Melatonin moves your body clock; magnesium tops up a mineral many people lack. Here is which one fits your sleep problem, and…

Pablo Vicento · October 15, 2026

Health

Protein before carbs: what food order does to blood sugar

Several small trials found that eating vegetables and protein before carbohydrates flattens the glucose curve after a meal. Whether that adds up…

Pablo Vicento · October 10, 2026

The Tested Weekly