What a chief of staff reads for you, and what it leaves alone
Opitor is an AI-native operating system for small companies, where every person gets their own AI chief of staff. Everything useful it does starts with reading. It cannot follow up a deadline it has not seen or draft a reply to a thread it does not know about.
Which makes the edges of that reading the first thing worth being clear about. Not as a policy document, but as the plain answer to a question anybody sensible asks in the first minute: what is it looking at.
What it reads
Three things, and the list is short on purpose.
Your messages, direct and group. The conversations you are part of. This is where commitments get made in a small company, so it is where most of the useful material is.
Your todos and their deadlines. What you have said you will do and when it is due, laid out on a calendar by due date. This is what lets it tell the difference between a busy week and a week where you have promised three things on the same day.
The company’s quarterly goals. The OKR the administrators manage. This is the context that makes the difference between a chief of staff that can only see your inbox and one that can tell whether what is filling your week has anything to do with what the company said it was doing this quarter.
That is the whole list. There is no crawl of your other tools, no connected accounts, no background collection of things you did not put in.
What it leaves alone
Other people’s private conversations. It works for you, so it reads what you can see. A conversation between two colleagues that you are not part of is not yours, and it is not your chief of staff’s either.
This holds in the direction people worry about most. If you are the founder, your chief of staff does not get a wider view because you run the company. There is no administrator override into private messages, which means there is nothing for an administrator’s chief of staff to inherit. The rule is a property of the system, not a setting somebody remembered to leave switched off.
It also leaves alone anything you did not confirm. After a conversation it proposes what it thinks is worth keeping. A proposal is not a memory. Until you confirm it, it is not used, and what does get kept is visible to you as a list you can look through and delete from.
The practical shape is that the boundary is the same for everyone: not a set of per-person permissions somebody has to maintain, and not a promise that holds until an exception is needed.
What it does with what it reads
Three things, and again the list is short because the limits are the point.
It proposes. Commitments it noticed in a thread become suggested todos, with a person, a task and a date attached. Things it thinks are worth remembering become suggested memories. Each one waits for you.
It drafts. It writes the reply you were going to write, knowing the thread and knowing what you already said. Getting from an empty box to a decent draft is most of the work in a message, and it does that part.
It reminds. It follows up your todos and their deadlines, so the thing you agreed to on Tuesday is still in front of you on Friday rather than depending on your memory of a scrolled thread.
What it does not do with it
It does not send. Not under any setting. It drafts, you send, and everything it writes is signed in purple, so when it wrote something you can see that it wrote it. The convenience of something that replies for you is real, and the cost is a company where you can no longer tell whether a message from a colleague came from that colleague.
It does not decide. It can tell you that three deadlines land on Thursday. It cannot tell you which one to miss, because that depends on which customer is fragile this month and which colleague you promised last time. That is your judgement and it stays yours.
It does not keep what you did not confirm. A memory you were never shown cannot be corrected, so nothing is used until you say so. Being able to see and delete a list matters much less than having been shown the entry in the first place.
Put those together and the shape is the same as the human job the name comes from. A chief of staff in a real company reads along, chases what was supposed to happen, prepares the material and writes the first version. They do not take your meetings or make your calls, and the reason is not modesty about their ability.
Why the boundary is what makes it usable
A company of ten has nobody whose job is to evaluate this. There is no security review, no procurement, no policy person. One person reads a page, forms a view in a few minutes, and either tries it or does not.
Under those conditions a long list of capabilities is not reassuring. It is the opposite, because every additional thing a system can reach is another thing you would have to check, and there is nobody to check it. What makes a decision possible at this size is a boundary small enough to hold in your head: it sees what you see, it proposes and drafts, it never sends and never keeps what you did not confirm.
That is four sentences. You can repeat them accurately after reading them once, which matters because the second person to use it in your company will hear about it from the first person rather than from a page like this one.
There is a second reason, which is about what people are willing to write. Every small company has conversations that are useful and uncomfortable: this is not working, I think we are wrong about the customer, I am struggling. Those happen somewhere. If the company’s own tool might be readable by the company, they move to a personal channel where nobody who could act on them will ever see them.
How to check it rather than take it on trust
Every claim on this page can be tested in an ordinary week of work by one person, before anybody else is involved.
Watch whether anything goes out that you did not send. Look at the proposals it made and see whether they came from threads you are actually in. Open what it has kept and check that each entry is something you confirmed. Delete one and see whether it comes back.
None of that requires you to believe a page. It requires about a week, which is roughly how long you should use it alone before a colleague sees it.
Where Opitor fits
This is how Opitor works today. Your chief of staff reads your messages, direct and group; your Todo List and its deadlines, laid out on a calendar by due date; and the company’s quarterly goals (OKR), which administrators manage. It proposes todos and memories, drafts replies and follows up deadlines. It never sends as you, everything it writes is signed in purple, administrators have no override into private messages, and nothing it proposes to remember is used until you confirm it, with everything visible and deletable. Every person gets their own, you start alone and invite your team when you are ready, and it is free to start with no paid plans yet. There is more on what is an AI chief of staff and on the questions and answers page.