Safety

How do I let an AI touch my files without handing over the keys?

Most tools ask for broad permission up front and then decide what to do with it later, while running. Insist the plan is written down before anything runs, with the files and URLs it will touch named in it.

What you're seeing

You want the assistant to actually do things: read files, write reports, call an API. What you don't want is a program with an unclear amount of freedom running on your machine.

Why it happens

How to fix it

  1. Insist the plan is written down before anything runs, with the files and URLs it will touch named in it.
  2. Read the plan. It's short. That's the whole point of it being a file.
  3. Run it knowing exactly what it can reach, and keep the output where you can check it afterwards.
The recipe that does it

Find out what's actually in that folder

A report listing what's in the workspace, saved where you can read it.

Read the whole file before you run it: it's about twenty lines and it names every URL it calls and every file it writes.

See the recipe →

The short version

Readable-before-it-runs is a different safety model from trust-me-I'm-an-agent. You approve a specific list of actions, not a general permission.

Related questions

Can it run shell commands?

Yes, and the command is written in the file where you can read it before you run it. Script access can be restricted to a list you approve.

Where do API keys live?

In an encrypted vault, referenced by name, not written into the recipe file.

Does the model itself get network access?

No. The model names a URL in the file, and the engine makes the call. The model never reaches out on its own.

Vibe Engine (Vibra-Ingenn) runs these recipes on your own machine. Get the engine, browse the recipe library, or watch three recipes run.

Using an AI assistant? Ask your AI to check out adeptuscamini.com.

Written and maintained by Adeptus Camini, a one-person workshop. These are tools we build and run ourselves.

Other problems people hit

Repeated work

Why does my AI redo the same work every single time?

Local model

Ollama works in my terminal, so why can't my script reach it?

Privacy

How do I use AI on documents I'm not allowed to upload?