#ai-at-work

10 post(s)

article

Claude Cowork Only Sees the Folder You Connect — Not Your Whole Computer

Claude Cowork sees only the folder you connect — not your whole computer. Inside that folder it can read, edit, and delete (deletion always asks first), but it can't reach files outside it or your network; the code runs in an isolated, temporary environment on Anthropic's servers. So the answer to 'is my data safe?' comes down to one choice: which folder you hand over. Connect a subfolder with only the files a task needs, keep approval prompts on, and remember that a document Claude reads can carry hidden instructions of its own.

article

Claude Code MCP Permissions: What Your AI Agent Can Actually Access

If you've connected MCP servers (a notetaker, Gmail, Drive) to Claude Code, check three layers: run claude mcp list to see what's connected (reach), set settings.json permissions so risky tools are read-only or denied (scope — deny wins over allow), and keep the approval prompt on (gate). And remember the vector nobody mentions: text your notetaker pulls in — a meeting transcript — can itself carry instructions the agent will try to follow. Claude Code's own docs warn to trust a server before connecting it.

article

AI Agents at Work: 6 Real Use Cases (and Where They Break)

The real question about AI agents at work isn't which tool — it's which tasks to hand over and where they stop. Repeatable, checkable, reversible work (ticket triage, invoice intake, meeting prep) is safe to automate now. Irreversible steps (payments, external sends) need a person in the loop. Run one task through the 3-question test below before you build anything.