Field notes
Practical incident response, browser-level proof, and honest product comparisons. Written for people who paste real work into AI tools.
Developer security
Privacy settings reduce data use, but they do not make live credentials safe prompt material. Use this practical checklist before sharing code with AI.
Read article →AI privacy
A plain-English guide to Claude’s consumer training controls, commercial products, Incognito chats, and the data you should still remove.
Read article →Developer security
Why .env files are unusually risky AI prompts, what to do after sharing one, and how to sanitize configuration without destroying useful context.
Read article →Comparison
A candid comparison of four local-first tools for keeping API keys, credentials, and PII out of AI chats.
Read article →Technical guide
A hands-on explanation of what leaves your browser when you send a prompt, how to inspect the request, and what masking changes.
Read article →Incident response
A practical incident-response checklist: revoke the key, inspect usage, replace it safely, and prevent the same mistake next time.
Read article →