What gets in the way?
- A quote request fans out to a dozen carriers, and the replies come back in any order and format.
- Closings stall on one missing document, and nobody notices until the deadline.
- Follow-up rules live in spreadsheets and cron jobs that drift from the mail.
How does nofeb handle it?
A thread per case
Lane, offered rate, deadline and owner, or checklist and documents received, as typed metadata on the thread. Attachments arrive with extracted text and are filed byte-exact.
Deadlines that wake the agent
follow_up_at on each thread; thread.due fires with the thread's metadata when it passes, and the agent chases or escalates.
The whole board in one query
query_threads looks across every desk's inbox and pod by metadata values and ranges and by the direction and age of the last message, so a supervisor agent can list every stalled case without opening a single thread.
Signings on the calendar
Each inbox has a calendar: find a slot that suits every inbox involved, book it, and the invitations go out by email; replies and cancellations update the event.
People on the exceptions
A coordinator opens the case in the webmail, takes the thread over, and the agent's sends on it stop until it is handed back; the metadata panel shows the case's state beside the mail.
What does the code look like?
for (const carrier of carriers) {
await nf.messages.send(desk.id, {
to: [carrier.email], subject: `Quote: ${lane}`, text: request,
thread_metadata: { stage: "quote_requested", carrier: carrier.id, follow_up_at: hoursFromNow(4) },
});
}
// thread.due arrives for every carrier that has not answered in four hours. curl -X POST https://api.nofeb.com/v1/threads/query -H "authorization: Bearer $NOFEB_API_KEY" \
-H 'content-type: application/json' \
-d '{"metadata": [{"key": "stage", "op": "=", "value": "quote_requested"}],
"last_message_direction": "outbound", "last_message_before": "now-4h"}' Where does nofeb stop?
- nofeb is not a TMS, e-signature or transaction-management system; it carries the conversations and their state.
Frequently asked questions
How do I follow up automatically when a carrier does not reply?
Set follow_up_at on the thread when you send; clear it when a reply arrives. thread.due fires for the threads that are still waiting.
Can a manager see every stalled case at once?
Yes: POST /v1/threads/query with the stage and last_message_direction and last_message_before filters returns them across inboxes and pods, with each thread's metadata.
Can different clients' mail be kept apart?
Yes: a pod per client, with keys and webhooks scoped to the pod.
Status of everything on this page
Every capability named above, with its status as reconciled against the engine.
| Capability | What it does | Status |
|---|---|---|
| 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 |
| Queries across threads by metadata | Find threads across inboxes and pods by typed metadata values and ranges, by decision probabilities, and by the direction and age of their last message (every thread at stage quote with no reply for four hours), plus an inbox directory searchable by metadata. | Shipped |
| Unlimited inboxes | Create as many inboxes as the work needs, with a generated or chosen address and an idempotent client reference. | Shipped |
| Pods | Sub-tenants inside one organization: one per end customer, created idempotently from your own customer id. | Shipped |
| Attachment text | Attachments are listed with their extracted text and can be downloaded byte-exact. | Shipped |
| Folders, keywords and labels | Folder roles with unread counts, plus keywords such as seen, flagged or your own labels. | 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 |
| Take a thread over from the agent | A person takes a thread over; until they hand it back, the agent's sends on that thread are held for approval or refused, and an event records who is driving. Works over the API, MCP, JMAP and the webmail. | 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 |
| 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 |