How we keep agents away from your money
These are rules in the code, checked by tests. They are not instructions we hope an AI follows.
-
Agents propose. People approve.
You decide which actions need a sign-off. Paying, pricing, deleting, ad spend and anything a customer sees always do. Routine reminders run on rules you switch on yourself.
-
Code does the math.
AI reads documents and drafts messages. Every dollar amount is calculated by ordinary, tested code, never guessed by a language model.
-
Everything has a name on it.
Every action, by a person or an agent, is logged with who, what and when.
-
New features start switched off.
Anything risky ships turned off. You turn it on once you have seen it work on your own data.
-
AI on a budget.
You set a monthly spending cap for the agents. They cannot go over it, and one switch stops them all.
-
Outside text is data, never orders.
A vendor email or a PDF cannot tell an agent what to do. And nobody changes bank details by email, ever.
Pick the first job for your agents
Tell us the one job you would hand off first. We will tell you honestly whether an agent can take it.