Marta
What Marta does without asking and what it does not
The line between looking things up and acting, and who decides where it sits.
The question always comes, and rightly: if the assistant can read everything of yours, what can it do with it? The short answer is that looking things up is one thing and acting is another, and the second is subject to what you decide.
The three layers
| Layer | Examples | Who authorises |
|---|---|---|
| Consulting | Summarising, searching, comparing, explaining | Your own permissions: it sees what you see |
| Preparing | Drafting, building a process, proposing a list | The same, but nothing leaves here |
| Acting | Sending, requesting from a third party, closing, approving | Configured, and by default it asks |
Important
The first layer is bounded by your permissions, not the assistant's. If you cannot see a file, it does not appear in an answer either: there is no back door through which the AI sees more than you.
Where to draw the line
- 1
Let it consult and prepare, always
That is where nearly all the time saving is and it can break nothing.
- 2
Let it act only on the reversible
Opening a task, sending a reminder, flagging something for review.
- 3
Have it ask on anything going outward
Anything reaching a third party is better with a person present.
- 4
And never on what decides
Approving, rejecting, blocking a supplier. Someone with a name answers for that.
Watch out
Point three is the one most quickly relaxed "because it's going well", and the one that goes worst when it fails: a wrong message to two hundred suppliers is not undone by a correction. What goes outward deserves a human glance even at thirty seconds' cost.
What gets recorded
That last point has a practical consequence: a rule firing a thousand times spends a thousand, and it is worth checking the breakdown in the first month it is switched on.
Worth knowing
You can start with no ability to act and widen it later. That is the recommended path: first check its answers are reliable in your case, and only then let it execute anything.
›Can it delete things?
Not something worth delegating, and by default it does not.
›Does it learn from our documents?
It uses them to answer you; see the article on what the AI does with your documents.
›Can I see what it has done?
Yes, in the activity log, like any user.
A real case
The situation
A company wants the assistant to send reminders and approve simple documentation.
What you do
- Lets it handle reminders and tasks
- Keeps approval with a person
What you get
Recovers the chasing time without delegating any decision it answers for.
The situation
It is expected to launch requests unprompted.
What you do
- Checks what it does on its own and what it does not
What you get
No unrequested actions are assumed.
The situation
It is asked to write to a supplier and nobody reviews.
What you do
- Reviews the text before sending
What you get
What goes out carries your judgement.
The situation
It is assumed a figure has been corrected.
What you do
- Checks the figure in its document
What you get
The real state is known.
The situation
It is asked something that requires a decision.
What you do
- Takes the decision and uses the answer as support
What you get
Each does their own job.
The situation
It is expected to act on files it cannot see.
What you do
- Checks its scope
What you get
Expectations are set.
This article answers
- can the ai do things on its own
- what actions does the assistant execute
- does the assistant send emails by itself
- limits of the ai agent