Autonomy Levels
Control how much human oversight is required before outbound emails are sent from each mailbox.
Autonomy levels let you control how much human approval is required before an agent can send email from a mailbox. This is a per-mailbox setting that governs the balance between speed and oversight.
Levels
| Level | Name | Behavior |
|---|---|---|
| L1 | Assisted | Every outbound send requires explicit human approval before delivery. |
| L2 | Guarded Auto | First message to a new recipient requires approval. Subsequent messages to known contacts send automatically. |
| L3 | Fully Autonomous | All policy-approved sends execute automatically. Only hard policy blocks stop a send. |
The default autonomy level for new mailboxes is L3 (Fully Autonomous).
How it works
When an agent sends an email, the autonomy level is evaluated after policy checks but before the email is queued for delivery:
- The send request passes through the policy engine (duplicate detection, rate limits, suppressions, etc.)
- If the policy allows the send, the mailbox's autonomy level is checked
- Based on the level, the send is either queued immediately or routed to the approval queue
L1 - Assisted
All sends are held for human approval regardless of prior contact history. This is the most conservative setting, ideal for high-stakes mailboxes or early-stage agent deployments where you want full visibility.
L2 - Guarded Auto
The system checks whether there is an existing conversation thread between the mailbox and the recipient. If this is the first message to a new contact, it requires approval. Once a thread exists with that contact, subsequent messages send automatically.
This balances safety with throughput -- agents can continue existing conversations freely, but new outreach is supervised.
L3 - Fully Autonomous
No autonomy-based approval is required. Sends execute as long as they pass policy checks. This is the right choice for production mailboxes with well-tested agents and established sending patterns.
Setting the autonomy level
Via the API
curl https://api.molted.email/v1/agent/mailboxes/:id/autonomy?tenantId=TENANT_ID \
-H "Authorization: Bearer YOUR_API_KEY"{
"autonomyLevel": 2,
"description": "First-contact approval -- only first message to a new recipient requires approval"
}curl -X PATCH https://api.molted.email/v1/agent/mailboxes/:id/autonomy?tenantId=TENANT_ID \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "autonomyLevel": 1 }'You can also set the autonomy level when updating a mailbox via PATCH /v1/agent/mailboxes/:id:
curl -X PATCH https://api.molted.email/v1/agent/mailboxes/:id?tenantId=TENANT_ID \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "autonomyLevel": 2 }'Via the CLI
molted mailboxes autonomy MAILBOX_IDmolted mailboxes autonomy set MAILBOX_ID --level 2Via the Portal
Navigate to Dashboard > Mailbox > Settings and use the Autonomy Level card to select your desired level.
Interaction with HITL
Autonomy levels work alongside Human-in-the-Loop (HITL) settings. If HITL is enabled at the tenant level, sends may require approval even if the mailbox is set to L3. The two systems are additive -- either one can trigger an approval requirement.
| HITL enabled | Autonomy Level | Result |
|---|---|---|
| No | L3 | Auto-send |
| No | L2 | Approval for first contact only |
| No | L1 | Approval for all sends |
| Yes | Any | Approval for all sends (HITL overrides) |
Approval flow
When a send is held for approval (due to autonomy level or HITL), it appears in the approval queue. Approvals can be managed via:
- The Portal approval dashboard
- The API:
GET /v1/send/approvalsandPATCH /v1/send/approvals/:id
Pending approvals expire after the configured timeout (default: 24 hours). Expired sends are not delivered.
Choosing the right level
| Scenario | Recommended Level |
|---|---|
| New agent deployment, testing behavior | L1 |
| Production agent doing outbound prospecting | L2 |
| Production agent sending transactional email | L3 |
| High-stakes communications (legal, finance) | L1 |
| Agent replying to inbound support emails | L2 or L3 |