What gets in the way?
- Connecting an assistant to a person's own mailbox gives it everything, including the power to send as them.
- Most people want the assistant to see some mail and prepare replies, and never to send without asking.
- Scheduling by email is half the job, and an assistant without a calendar can only suggest times.
How does nofeb handle it?
Its own address
The assistant writes from its own inbox, so recipients know who they are dealing with and the person's mailbox stays theirs.
The person's mail, by forwarding
A forwarding address per person accepts mail only from the addresses they forward from, keeps the original sender, and surfaces the Gmail or Outlook confirmation code so setup finishes without anyone digging through a mailbox.
A calendar it can run
Invitations that arrive by email land on the inbox's calendar; the assistant answers them, finds free time inside working hours, books meetings that send the invitations, and sees counter-proposals and cancellations as events.
Drafts the person sends
The assistant writes drafts; the person edits and sends them from the webmail or from their own mail app over IMAP. send_with_approval holds anything the assistant tries to send itself, and its key cannot approve.
What does the code look like?
curl -X POST https://api.nofeb.com/v1/inboxes/$ASSISTANT_INBOX/forwarding-addresses \
-H "authorization: Bearer $NOFEB_API_KEY" -H 'content-type: application/json' \
-d '{"person_email": "ana@example.com", "label": "Ana"}'
# Ana sets her mailbox to forward to the returned address; the confirmation
# code appears on the address and in a forward.confirmation event. // The agent's inbox runs at send_with_approval.
const sent = await nf.messages.send(inbox.id, { to: ["dana@example.com"], subject: "Quote", text });
sent.status; // "awaiting_approval"; approval.requested goes to your webhooks
// Later, from a tool a person uses, with a key that holds send:approve:
await approver.sends.decide(sent.send_id, { approve: true }); // approval.decided; sent exactly as held Where does nofeb stop?
- The assistant works on the mail forwarded to it; nofeb does not act inside the person's own Gmail or Outlook mailbox or send as their address.
Frequently asked questions
Should an assistant agent use my email account?
It is safer to give it its own address and approval before every send. You forward what you want handled; it never holds the keys to your mailbox.
Can the assistant accept meeting invitations?
Yes. Set the inbox's auto-accept to never, known senders or always, choose what happens on a conflict, or let the agent answer each invitation itself with respond_to_invite.
Can the assistant send without asking?
Only if you move its inbox to a more autonomous tier. At send_with_approval, nothing leaves without you.
Status of everything on this page
Every capability named above, with its status as reconciled against the engine.
| Capability | What it does | Status |
|---|---|---|
| Unlimited inboxes | Create as many inboxes as the work needs, with a generated or chosen address and an idempotent client reference. | Shipped |
| Forward to an agent | Per-person forwarding addresses that bring someone's own mail into their agent's inbox byte for byte, accepting only mail traceable to the senders you allow. Gmail and Outlook forwarding-confirmation codes and links are recognised and surfaced, and each address can be rotated or revoked. | Shipped |
| Calendar per inbox | A calendar on every inbox: events with recurrence and time zones, invitations, updates, cancellations and replies by email, auto-accept rules, free/busy, availability and booking that sends the invitations, MCP tools for scheduling, and CalDAV and JMAP Calendars for standard clients. Invitations an agent sends follow its inbox's autonomy tier. | Shipped |
| Drafts | Agents write drafts that a person edits and sends, over the API, MCP, JMAP, IMAP and the webmail. It is the documented path for draft-only inboxes: sending a draft needs the approval permission agents do not hold. | Shipped |
| Webmail for the humans in the loop | A full webmail and calendar on the same mailboxes the agents use, with an agent-activity timeline, the approval queue, a per-thread driver lock and a metadata panel, signed in through the same accounts as the console. It opens with hosted access. | Shipped |
| IMAP and POP3 | IMAP4rev2 (with IMAP4rev1 compatibility, IDLE, CONDSTORE and QRESYNC) and POP3 on every inbox, over TLS only, signed in with the inbox address and an API key or a revocable per-inbox app password. | Shipped |
| Autonomy tiers enforced by the server | Every inbox carries a sending policy, from read-only to autonomous, enforced on the server for every surface that sends, so switching from the API to MCP cannot bypass it. | Shipped |
| Human approval of held sends | A held send waits with status awaiting_approval until a human approves or rejects it; both steps emit events. The approval queue lists every held send with its recipients (each marked if new to the conversation), the reasons it was held and who submitted it. Approving needs the separate send:approve scope, which keys from agent self-signup never hold, so an agent cannot approve its own send. | Shipped |
| Typed metadata on messages, threads and inboxes | Merge-patch keys onto a message, a thread or an inbox, and declare a key's type so every write to it is validated. | Shipped |
| Follow-up timers | Set follow_up_at on a thread and, when that time passes, a thread.due event carrying the thread's metadata goes to your webhooks and the event feed, so agents need no scheduler of their own. | Shipped |
| safe_body for untrusted mail | The message's new text with zero-width and direction-altering characters, hidden HTML and forgeable quoted history removed, wrapped in a provenance header that tells the model whose words these are. | Shipped |