For Samantha

Articles that came out of our calls — things I said I’d look into or wasn’t sure about, checked against primary sources. Each ends with what was verified, when, and what stays inferred.

• What actually protects you when an agent has your files — and how real is prompt injection?
• Does AI tooling really come to Mac first, and what specs does it need?
• What can Claude’s stock Asana connector do, and when do you need more?
• What can an AI do in your browser, and how do you keep it away from sensitive sites?
• Can you move your Claude chats and projects to another account?
• What do Claude’s plan tiers buy, and when does overage beat upgrading?
• Who owns, sees, and trains on your chats on a Claude Team account?
• Which Codex model, reasoning effort, and access settings matter?
• What can Claude see through a connector, and how do you scope it down?
• Why does AI search of Google Drive miss documents, and what fixes it?
• Does GDPR let you put other people’s data into a personal AI account?
• How much context can you feed an AI before quality drops, and when should you restart?
• Where should standing context live — memory, project instructions, or files?
• What does Raycast add over Spotlight for AI-era quick capture?
• Sandboxed or full-access: what isolation do coding agents really have?