There is a quiet assumption in most AI products: that the goal is an agent which acts on its own. The more it does without you, the better it supposedly is. We don’t build toward that. The goal was never an AI that acts alone — it’s an AI you can trust to act. Those are not the same thing, and the difference is the whole point.
An agent that acts alone asks you to trust it in advance, before you’ve seen what it will do. An agent you can trust to act earns that standing one decision at a time, where you can watch. We chose the second. It is slower to look impressive and far harder to regret.
The agent proposes; a person commits
Everything our agents do begins as a proposal, not an action. When an agent decides a record should change, a message should go out, or a relationship should be updated, it doesn’t reach into the system and do it. It drafts the change and sets it down for a person to look at. Nothing touches the live system until someone approves it.
This is what we mean by suggest-mode. The agent does the work of thinking — reading the situation, drafting the response, proposing the update — and a person does the work of deciding. The human stays the author of record. When the change finally lands, it lands under a person’s approval, with the agent’s draft and the reason both attached to it. You are never in the position of discovering, after the fact, that something acted in your name while you weren’t looking.
The cost is obvious: a person is in the loop, so the loop is not instant. We think that cost is the feature. The moment of approval is the moment trust is actually exercised, rather than assumed.
Sending it back is a teaching signal
Approval is not the only move. The more interesting one is sending the work back.
When a draft isn’t right, you don’t just reject it — you return it with a revision note: this is close, but the tone is wrong; you missed that this customer is mid-dispute; check the figure before sending. That note is not only a veto. It is a correction the agent can learn from, an instruction in the specific language of your business that no generic model could have known on its own.
A plain yes/no would throw that signal away. By treating the revision note as a first-class part of the flow, every rejected draft makes the next one better. The human isn’t just a gate the work has to pass through; they are the source of the judgment the agent is being shaped by.
Authority is earned, not granted
Not every action deserves the same scrutiny forever. An agent that has proposed the same kind of change a hundred times, and been approved a hundred times, has earned something a brand-new agent hasn’t.
So latitude grows with track record. A new agent’s every move is reviewed closely, the way you’d check an intern’s work before it goes out. As its proposals prove reliable in a given area, the review on that area can loosen — the same way a junior colleague becomes a senior one and stops needing a second pair of eyes on routine work. Authority is earned through a history of good decisions, not granted on day one because the software shipped.
Crucially, this is a setting you control, not a threshold the system crosses on its own. The trajectory from closely-watched to trusted is one you author, deliberately, as the evidence accrues.
Where this stands
This is a design principle we’re committed to and actively building, not a finished product with a track record to point at. We’re describing how the approval flow is meant to work because the shape of it — propose, review, approve or revise, then commit — is the part we want to be judged on, before there are numbers to show.
We’d rather tell you how control is meant to feel than demo an agent doing something impressive on its own. The impressive demo is the easy part. The harder, more honest commitment is that a person stays in the decision.
Delegation only feels safe when you can take it back. An agent you can stop, correct, and overrule is one you can actually hand work to — because handing it over was never irreversible. Control isn’t the opposite of delegation here. It is the thing that makes delegation possible at all.