What gets in the way?
- Shared sending domains inherit their noisiest tenant's reputation, and mailbox providers now reject non-compliant bulk senders.
- An agent with a send tool and a list will happily write to a thousand strangers before lunch.
- Follow-up logic lives in a scheduler that drifts from the mail it is about.
- An agent that writes the wrong thing to a prospect costs more than the meeting it was trying to book.
How does nofeb handle it?
Your domains, set up and warmed up
Add a domain and nofeb publishes its DKIM, MAIL FROM and DMARC records through your DNS host's API where it can, checks them live, and puts it on a daily warm-up ramp. Sends over the day's cap wait for the next day; nothing is dropped.
Brakes the agent cannot release
Sending pauses for the whole organization when the bounce or complaint rate crosses its threshold, until a person resumes it. Caps per inbox and per API key bound sends per hour and per day and new recipients per day, and a recipient blocklist refuses customers and competitors on every tier.
Replies sorted before the agent writes
Every reply carries typed decisions (intent, needs-reply, automated, requires-human) with probabilities, and query_threads finds every thread at a stage whose last outbound message has gone unanswered.
Mail that says who wrote it
Register each SDR agent with its human sponsor; its mail is signed so anyone can verify which agent sent it, and AI disclosure adds AI-Generated headers and an optional footer to agent-written mail.
Approval before autonomy
Run new agents at send_with_approval; every send waits as awaiting_approval for a person with the send:approve scope. Hard bounces and complaints are suppressed automatically.
What does the code look like?
curl -X PUT https://api.nofeb.com/v1/policy/settings -H "authorization: Bearer $NOFEB_API_KEY" \
-H 'content-type: application/json' \
-d '{"scope": "inbox", "inbox_id": "'$INBOX_ID'",
"settings": {"caps": {"sends_per_day": 80, "new_recipients_per_day": 25}, "over_cap": "hold"}}'
curl -X POST https://api.nofeb.com/v1/policy/lists -H "authorization: Bearer $NOFEB_API_KEY" \
-H 'content-type: application/json' \
-d '{"list": "recipient_block", "pattern": "competitor.example", "scope": "org", "note": "competitor"}' // 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?
- nofeb will not help mail people who did not ask to hear from you at volume, and it is not a sequencer or a CRM: your agent decides what to write and when.
Frequently asked questions
How do I keep AI SDR email out of spam?
Send from your own authenticated domain (DKIM, SPF via a custom MAIL FROM, DMARC), warm new domains up gradually, keep each tenant's reputation separate, stop mailing addresses that bounce or complain, cap how many new people each agent may write to, and keep content human-reviewed while an agent is new. nofeb does each of these on the server.
What happens if bounces spike?
When the permanent-bounce or complaint rate over the evaluation window crosses its threshold, new external sends are refused with sending_paused, queued ones wait, and sending.paused goes to your webhooks. Resuming releases the waiting sends and restarts the window.
Should AI outbound use a separate domain?
Many teams use a dedicated sending domain or subdomain so outbound reputation cannot affect the main domain's mail. nofeb sets up any domain you add, with records published at your DNS host where it can.
How do I keep a human in the loop on AI-written sales email?
Put the inbox on send_with_approval. Every send is held, a webhook tells your approval tool, and only a key with send:approve can release it.
Status of everything on this page
Every capability named above, with its status as reconciled against the engine.
| Capability | What it does | Status |
|---|---|---|
| Custom domains | Add a domain and nofeb returns its DKIM, custom MAIL FROM and DMARC records, plus an inbound MX if you want nofeb to receive its mail, checks them, and emits domain.verified when they pass. | Shipped |
| DNS setup made easy | nofeb detects who hosts your domain's DNS and gives you the shortest path for that host. It can publish the records through the Cloudflare, DigitalOcean, Hetzner DNS, Vercel, Porkbun or Gandi API with a token used for that one call and never stored, and it never deletes a record. Every other host gets step-by-step instructions in its own terms, plus zone-file, Route 53 and Terraform exports. A live check shows each record's status, what was found and the likely mistake. Pointing your MX at nofeb is a separate choice, so publishing sending records never moves your mail. | Shipped |
| Managed sending with per-tenant reputation isolation | nofeb sends on your behalf from your verified domain, and each organization can send with its own isolated reputation, so one sender's behaviour cannot damage another's. | Shipped |
| Delivery events and automatic suppression | Delivery, bounce and complaint reports arrive as events, and hard-bounced or complaining recipients are suppressed automatically. | Shipped |
| Automatic pausing and warm-up | New custom domains follow a daily warm-up ramp; sends over the day's cap wait for the next day instead of being dropped. If an organization's bounce or complaint rate crosses its threshold, sending pauses automatically and an event says so; resume it by API or in the console. First contact per inbox is throttled by default. | Shipped |
| Per-agent rate and recipient caps | Limits per inbox and per API key on sends per hour and per day, distinct recipients per day, recipients per message and new recipients per day, checked and charged in one step so concurrent sends cannot overshoot. A usage call shows the budget left, and you choose whether an exhausted cap holds a send for approval or refuses it. | Shipped |
| Recipient and sender allowlists and blocklists | Lists of addresses, domains or wildcards per organization, pod or inbox: who an agent may write to, and whose mail it reads. A blocked recipient is refused on every autonomy tier, a blocked sender's mail is rejected or quarantined, and you choose whether a send outside the allowlist is held for approval or refused. A check call predicts what a send or an inbound message would meet before it happens. | Shipped |
| Decisions on every message | A default set of typed decisions on every inbound email (intent, urgency, needs-reply, automated, verification email, phishing, injection risk, requires-human and language) with a probability each, your own decision schemas beside them, human relabels that correct and retrain it, per-question accuracy and calibration stats, and confidence-gated sending for the send_when_confident tier. Decisions run without leaving nofeb by default; a third-party model sees mail only if you opt in. | 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 |
| Agent identity and signed mail | Register each agent with a name, a human sponsor and the keys it acts through. Its mail carries an agent header and a signature over the sender, recipients, subject and body that anyone can check against your organization's published keys or nofeb's verification call. Revoking an agent stops its keys from sending and marks its mail as revoked. | Shipped |
| AI-generated disclosure | Per organization, pod or inbox, mail an agent sends carries AI-Generated and AI-Disclosure headers and an optional footer. Mail a person sends from the console or the webmail never does. | 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 |
| 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 |
| 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 |