Docs/ AI & automation

Authority modes — Manual, Copilot, Autopilot

Graduate the agent’s autonomy from suggestions to bounded action.

Aiemaily lets you choose exactly how much the agent does on your behalf. A global default applies across all threads, and agent-behaviour rules can override it per context — so high-trust senders can run on Autopilot while cold mail stays on Manual.

The three authority modes

Every thread in Aiemaily is processed under one of three authority levels. You set a global default in Settings → AI, and individual agent-behaviour rules can narrow or widen that default for specific senders, labels, or thread patterns.

The mode controls whether the agent takes action autonomously, stages work for your approval, or stays silent until you ask.

ModeWhat the agent doesHuman touch-point
ManualSummarises and answers questions on demand; nothing happens until you askYou initiate every action
CopilotTriages every new thread, drafts replies, proposes actions — all staged and waitingOne click to send or dismiss; nothing leaves without you
AutopilotWithin your configured bounds, sends, schedules, and files on its ownYou review the audit log and can cancel within the undo window

Autopilot guardrails

Autopilot is never a free agent. A set of configurable guardrails determines when it acts and when it escalates to you. All five guardrails apply simultaneously; the first one triggered causes the agent to stage the action for your review instead of sending.

  • Confidence floor — default 0.8; any reply the agent rates below this threshold is escalated rather than sent
  • Domain allow-list — autonomous sends only go to domains you have explicitly trusted; everything else is staged
  • Send-delay window — a configurable countdown after the agent queues a send, giving you real-time undo
  • Working-hours limits — restrict autonomous sends to specific days and times
  • Standing instructions — natural-language rules the agent follows before composing any reply (e.g. “Always CC legal on contract threads”)

Mandatory approval in v1

In the current release, Copilot mode is the highest level of autonomy available for sending. Autopilot send is being rolled out gradually with per-account gating. When Autopilot is enabled for your account, the guardrails above are always enforced and cannot be disabled.

Adopting autonomy gradually

The recommended path is to start on Copilot, watch the agent’s drafts for a week, then promote trusted sender groups to Autopilot one rule at a time. This gives you a clean sense of the agent’s quality before you hand over send authority.

  1. 1

    Set global default to Copilot

    Go to Settings → AI → Authority and choose Copilot. All threads now get staged drafts with one-click send.

  2. 2

    Review staged drafts for one week

    Use the confidence score and reasoning pane on each staged reply to calibrate how well the agent knows your voice.

  3. 3

    Create a behaviour rule for trusted senders

    In Rules ⚡ Brain, add a rule matching your trusted domain list and set its authority to Autopilot with your desired confidence floor.

  4. 4

    Tune guardrails

    Adjust send-delay, working hours, and standing instructions until the behaviour feels right. The audit log shows every action the agent took and why.

  5. 5

    Expand the allow-list over time

    Add more domains or sender patterns to Autopilot rules as confidence builds. You can always revert a rule to Copilot without losing its other settings.

Changing modes mid-thread

You can override the authority mode on any individual thread from the thread action bar. This is useful when a normally routine thread suddenly becomes sensitive — drop it to Manual with one click and the agent will not act on it autonomously until you lift the override.

Thread-level overrides take precedence over both the global default and any matching behaviour rule.

Start narrow, expand gradually

Giving the agent Autopilot on a small, well-defined sender group is far more effective than a broad Autopilot default. Narrow rules produce predictable, auditable behaviour.

Frequently asked

Feature overview

Copilot & Autopilot

Ready to try it?

Start free