Help Center
DocsAI Agent Steps
Hand a step to an AI agent that decides what to do inside the limits you set: the actions it may take, how much it may do on its own, and your plan's monthly AI credits.
Most steps do exactly one fixed thing. An AI Agent step is different: it hands the record to an agent that looks at the context and decides which of its allowed actions to take. You do not script the decision; you set the boundaries, and the agent works inside them.
Use an agent step when the right move depends on judgement a fixed rule cannot capture, like drafting a reply that fits the thread or deciding which of several follow-ups suits a given deal.
| Field | Description |
|---|---|
| Name* | A label for the agent step so its purpose is clear in the flow and the run history. |
| Allowed actions | The exact set of CRM actions this agent may take, grouped by what they do: Looks up, Drafts, Changes records, Sends and shares, Money and deletes. The agent can never act outside this list. |
| How much it may do on its own | One of two levels, deciding how much runs without asking. See the levels below. |
| Per-action permission | On each action that changes something: Allow, Ask first or Never. Reads are never permissioned. |
| AI credits | Automatic. Agent usage counts against your plan’s monthly AI credits, and an agent that reaches its share pauses and resumes on its own. Nothing to configure. |
| Field | Description | Default |
|---|---|---|
| Ask before acting | Looks things up and prepares drafts. Asks before changing, sending or deleting anything. Your first weeks with an agent, and anything a customer will see. | Asks first |
| Act automatically | Everything you have allowed. You read what it did in the run history. Summaries and internal briefs you read after the fact. | Automatic |
Always asks, whatever you choose: deleting records · sending anything to a customer · taking or refunding a payment · anything that cannot be undone.
That line holds at every level and is not a setting. Each action that changes something also carries its own permission, and when the two disagree the order is fixed: Never wins, then the always-asks floor, then Ask first, then Allow, and only then the level. There is no score and no threshold anywhere in that decision.
Reply drafts appear as email arrives, set in your email settings, not by an agent.
Reply drafts now appear as email arrives. Laureo reads each new email from a person once, as it arrives, and when the email needs your reply it prepares one draft, grounded in the message and in the linked record where there is one. When you open the email the draft is waiting in the reply box, with one line that says why it was written: edit anything you like, then send it when you are happy. Newsletters, notifications, automated mail and shared inboxes like billing@ never get a draft.
Two settings decide it, both in Email settings under AI in your inbox. Draft replies for is each person’s own choice of whose email gets a draft: People in your CRM, Everyone else who writes to you and Cold outreach replies. Draft replies when email arrives is the workspace switch an admin uses to turn reply drafting on or off for everyone.
The Inbox Assistant was the preset agent that used to write these drafts. New workspaces no longer receive it. Where it is still installed, it writes no drafts itself and acts only as the workspace switch: while it is active, drafting is on, and pausing it on the Agents home turns drafting off for everyone. Once it is retired, its card on the Agents home reads Reply drafts now appear as email arrives. with a link to Open email settings, and the admin switch takes over. Drafts are only visible to the mailbox owner.
Because an agent step uses your AI credits, it is often worth placing a Filter or If / Else before one so the agent only runs on records that matter. The agent step itself can also carry a condition the record must meet first, which keeps your AI credits pointed at the work you care about.