Is it safe to give an AI agent access to my email and accounts?

It can be, if four things are true. The agent asks before it sends or deletes, it never sees your passwords, it treats what it reads as untrusted, and you can see and undo what it did. Without those, don't.

Updated

What can go wrong

Email is the riskiest thing to hand an agent, because it is where strangers can write to it.

A checklist before you connect anything

CheckWhat good looks like
SendingDrafts are free; sending waits for your approval, at least at first
DeletingAsks first, or can be undone
Untrusted contentMessage text is marked as untrusted, and actions that send data out ask after reading it
SecretsPasswords and codes are filled in by the system, never shown to the model
ScopeYou grant only what the job needs: read-only, or one mailbox
RecordA step-by-step log of what it read and did
DisconnectRemoving the connection removes the access, and you can check
TrainingA plain statement that your data isn't used to train models, or a server you run
SpendingPayments always ask
A flow diagram of how an approval works in Casama. The bot works until it reaches a risky step such as sending, paying, deleting or publishing. It pauses and asks you; waiting costs nothing, and no answer in 24 hours counts as a deny. If you approve, the bot carries on. If you deny, the step does not run. Separately, a checkpoint is saved before a destructive command so the computer can be restored.
A risky step waits for your answer: approve and the bot carries on, deny and the step doesn't run.

Start small

  1. Connect one account with read access only.
  2. Let the agent sort and summarise for a week.
  3. Allow drafts. Read them.
  4. Allow sending with approval.
  5. Only then, allow routine replies it has got right many times.

What Casama does

How Casama keeps bots safe covers the rest.

Join the waitlist Run it on your own server