Skip to main content
The level of the account an action would use sets how far Hive goes — in Ask, in Signals, and for an agent’s or a workflow’s selected actions: on Read Hive only tells you what it found, on Draft it asks you first, and on Act, where new accounts start, it acts on its own — only inside the limits on this page, and never for the actions that matter most. This page explains the vocabulary and the exact order of checks behind every decision. The key idea: the AI model proposes; a deterministic policy engine decides. The model never holds credentials and cannot talk its way past a limit. Every proposed action is a typed request that passes rule-based checks before anything happens: the full gate below in Ask and Signals, and the account’s level, where it sends and the workspace’s limits for an agent’s selected action or a workflow’s action step.

Blast radius: how much could go wrong

Every action has a blast-radius tier describing how wide, costly or hard to reverse it is: The review panel turns the tier into a risk word: Low risk (B0), Medium risk (B1–B2), High risk (B3–B4).

Reversibility

Hive also classifies every action by whether it can be undone within minutes (the “five-minute undo test”):
  • Reversible — drafts, internal notes, document edits.
  • Compensatable — can be followed by a correcting action: sending an email or message, pausing or resuming, enrolling, escalating.
  • Irreversible — refunds, charges, revoking access, deletions. Any action type Hive does not recognise is treated as irreversible.

The autonomy ladder

Each action type sits on one rung: Moving one action type up the ladder never promotes any other. In Ask and Signals, an account set to Act treats a Suggest or Approve each action as Auto in limits, and a Shadow action stays observe-only. To keep an account’s actions on approval, set it to Draft.
Five-rung ladder from Shadow to Autonomous with human controls around it.Five-rung ladder from Shadow to Autonomous with human controls around it.

Autonomy is earned one action type at a time.

The decision gate, in order

For every action Hive proposes in Ask (a chat with no agent picked) or Signals, its policy engine checks, in this order:
1

Kill switch

If the workspace kill switch is on, the action is shadowed — recorded, never run. Nothing gets past this.
2

Account level

The level of the account the action would use. Read → Hive tells you what it found and takes no action. Draft → nothing runs without a person’s approval. Act → a Suggest or Approve each action is treated as Auto in limits, so it runs on its own only if every check below passes. Bulk actions, saving a file to Drive, tools on MCP servers and a plan you ask for with Act on this in Signals still come back as an approval card.
3

Rung

Shadow → shadowed. Suggest or Approve each → sent to a person for approval.
4

Limits (Auto in limits and Autonomous)

The action may run on its own only if all of these hold: the amount is within the per-action spend cap; the tier is at or below the workspace’s tier threshold; confidence is at or above the confidence threshold; the action is not irreversible; and the hourly action rate, per-action and windowed spend caps and error budget all pass. Anything that fails goes to a person instead. If an action type’s error budget is exhausted, it drops one rung.
5

Overrides that always win

Even when everything above passes, Hive always asks a person for B4 actions, for irreversible actions, and for B3 actions below the high-confidence threshold.
An agent’s selected action or a workflow’s action step follows the same first two checks — the kill switch, then the account’s level and any workspace ceiling: Read takes no action and Draft leaves an approval card. On an Act account, selecting it is the go-ahead, so the rung, the tier and confidence limits and the overrides above do not hold it back: it runs straight away and is recorded in the audit log. It waits for you as an approval card when where it sends (a recipient, channel, number or link) did not come from the agent’s instructions, the workflow’s own steps or words you typed in Hive: see Where an action sends. It also waits for the actions that always wait for a member’s click, such as a LinkedIn post, for a workflow step that changes something through a connected MCP server, which follows that server’s level, and in an agent run in which your own message asked for a draft. Of the checks on this page, only the kill switch, the hourly action limit, the spend caps and an agent run’s write budget can stop it. The error budget does not: an action that keeps failing pauses on that account only (see When an action keeps failing). Hive then refuses it and says why; a limit never turns it into an approval card. To make a workflow wait for a person, add an Approval step. See What agents and workflows do by themselves.

Default limits

Hive uses these defaults. You can set your own spend caps; the other limits are fixed, and Hive can raise the confidence thresholds (and lower the tier limit to B2) for a while when too many recent automatic actions could not be verified: The confidence and tier limits apply in Ask and Signals. An agent’s selected action or a workflow’s action step on an Act account runs at any tier and confidence, but the spend caps and the hourly action limit still apply. Owners and Admins can change the spend caps under Money guardrails · hard ceilings on the governance page — see Safety and control.

Where you manage autonomy

Open Settings → Products → Governance (the Policy & autonomy page). It has these sections:
  • Blast radius — the tier definitions, for reference.
  • Per-action autonomy · the safety ladder — the rung recorded for each action type. Changing a rung needs the Admin or Owner role. Today a change here is recorded as your policy and in the audit trail; the live gate still uses each action’s built-in rung. When the workspace has no configured action types, the section reads No actions configured yet.
  • Money guardrails · hard ceilings — the Per-action cap and Daily cap.
  • Integration accounts · Read, Draft or Act ceilings — Owners and Admins can cap a provider’s accounts at Draft or Read — in Ask, in Signals, and for agents’ and workflows’ selected actions; a ceiling only ever lowers a member’s own choice. See Workspace ceilings.
An autonomy-promotion proposal appears only for a department that has one; the whole-business view shows none.
Workspaces taking part in the Signals pilot cannot raise an action type’s rung while the pilot runs: promotions are frozen, and lowering a rung is always allowed.

Routine signals on an Act account

When the account a signal came from is set to Act (see Read, Draft or Act), Signals handles routine signals on that account by itself, as the account’s owner. A signal is routine when its rule asks for review only because it grants no autonomy of its own, and its blast radius is known and low. Every signal on a matter is routine, whatever amount or severity it shows: the account’s setting decides, and the limits below are the guard. A chase is the exception: it always waits for you (below). Everything in the decision gate still applies: the kill switch, the spend, rate and error limits, and the overrides for high-impact, irreversible and low-confidence actions. When any of them says no, you get a card instead. The decision is recorded with the reason “Act account: routine hold released to run within limits”, and on a matter the timeline says what Hive did and why. These always wait for you, whatever the account’s setting:
  • an action with a high or unknown blast radius, or one that moves money, such as a refund;
  • anything you asked for yourself: Act on this, a request in Ask, a meeting recap;
  • a signal with an active exception rule;
  • a signal read from several members’ accounts;
  • a chase — a requirement chase or an Invoice to chase — as a reply in your thread or as a new email;
  • a reply that mentions something Hive could not verify (see Replies are checked against what Hive read).
On a Draft account the signal leaves a card; on Read it only tells you. If one step of a plan needs you, the whole plan comes to you as one card.

Email replies on an Act account

A sent email cannot be undone, so every email Hive writes in Ask or Signals is blast-radius B4 and comes to you as a High risk card, on Act as on Draft. There is one exception. On a Gmail or Outlook account set to Act, Signals sends a reply inside your own email thread by itself: a reply you owe. A chase never goes out by itself, in your thread or not — neither a requirement chase nor an Invoice to chase: Hive prepares it as a draft that waits for your approval. A reply you owe goes out by itself only when all of these hold:
  • the thread is in your own mail on that account, and you wrote in it or were a direct recipient (never only copied);
  • the reply goes to someone who already wrote in the thread or was a direct recipient of it, never to someone new or someone who was only copied;
  • you have already replied to that exact address yourself, in that thread or before it began. What counts is a reply you wrote to a person’s own email that Hive still holds: a new email you started, a reply to a mailing or newsletter, or a reply to mail Hive no longer holds does not. Writing somewhere in the thread is not enough either: someone else could reply into your thread, and only an address you have written to counts. Hive counts only mail your Gmail or Outlook account itself filed as sent (Gmail’s Sent label, Outlook’s Sent Items) and goes by the provider’s own times, never by the From or Date a sender writes, so a forged email cannot pass as yours. Only mail you wrote yourself counts: a meeting response (accepting or declining an invitation), an automatic or out-of-office reply, an unsubscribe request, a read receipt or a delivery report does not, even though it sits in your Sent mail, and when Hive cannot tell, it does not count. An address a mailing gives for unsubscribing never counts. Mail Hive stored before this check existed does not count unless Hive reads it again, so an older correspondence may need one reply from you first. Anything else is a first reply: it comes to you as a card that says “first reply to this sender — please review”, because anyone can email you;
  • the message being answered names exactly one address to reply to (one sender, and at most one Reply-To), counting every address in it, even one Hive does not show;
  • Hive wrote the reply from that thread alone: to prepare it, it read that thread and nothing else — no other thread, no matter, no connected app, no Brain or knowledge search, no MCP tool — and every figure, link and address in the reply appears in that thread or in the signal itself. Otherwise the card says “Act account: this reply waits for you because Hive read more than this thread to write it.”;
  • the thread had activity in the last 14 days;
  • the signal was raised after this feature reached your workspace. Cards that were already waiting stay cards.
Every check in the decision gate still applies on top: the kill switch, the hourly rate limit, the spend and error limits, a pause on the account after repeated failures, and the 60 emails a day a seat may send by itself. Every other email Signals would send, a new email to anyone included, comes to you as a card. When a reply waits for you instead, the card’s reason says why, for example “this thread has had no activity in the last 14 days”. Each reply sent this way gets a receipt in your Inbox: the email’s subject, who it went to, the account it went from and the rule that let it go (“Sent by itself (Act): a reply in your own thread, to someone already in it whom you have written to, with activity in the last 14 days”). The receipt links to the signal, and the matter’s timeline says what Hive sent and why. If the account never gave Hive permission to send mail, nothing is sent and the receipt says so, with what to do: reconnect the account and allow sending. An email cannot be recalled once it has been sent, so there is no undo; set the account to Draft if you want to approve every reply first.

Earned autonomy

Hive notices when your team keeps approving the same kind of action. When the same pattern has been approved three times within 30 days, Hive offers to automate it.
  • Accepting creates an “Auto-run” rule in Learned behaviours. It becomes active straight away, so matching actions Hive prepares on its own for a signal run automatically within limits, unless the account the action uses is on Draft or Read; a plan you ask for with Act on this still waits for you. Engaging the kill switch demotes it back to Shadow.
  • An earned automation can rise at most to Auto in limits. It can never reach Autonomous on its own.
  • Hive never offers to automate a B4 action — sending an email, pausing a campaign, issuing a refund, revoking access — however often you approve it. A “send email” automation accepted earlier no longer appears in the list and no longer sends by itself: each email comes to you as a card again.
  • A Do not run decision, or an action that ran but could not be verified, creates an exception rule telling Hive not to auto-run that shape of action.
You can decline an offer; Hive keeps asking first.
A more rigorous, evidence-based promotion process — minimum numbers of trials per rung and measured success rates — is being prepared. It will only ever propose a change for a person to decide; it never grants autonomy by itself.

Promote safely

Before raising an action type’s rung:
  1. review enough completed examples to cover normal and unusual cases;
  2. confirm failures were caught and corrected;
  3. make sure the money and volume limits are explicit;
  4. prefer reversible actions; and
  5. keep sensitive customers and high-blast-radius actions on approval.

Review and approve

Decide on what Hive proposes.

Safety and control

Kill switch, policy page and spend caps.

Audit log

Every action’s receipt.

Learned behaviours

Rules, workflows and exceptions Hive has learned.