What gets in the way?
- AP runs on PDFs from a known set of vendors, and the expensive failure is a convincing email from someone who is not one of them.
- Bank-detail changes arrive by email and must never be acted on automatically.
- Auditors ask where the data lives, who touched it, and how long it is kept.
How does nofeb handle it?
Invoices as fields
Invoice vendor, number, total, currency and due date, and receipt merchant, order number and total, are extracted into typed metadata on arrival, with account numbers masked. Your own extraction schemas run on your own model key, validated against the schema.
Who really sent it
Every message is labelled trusted, known, unknown or suspicious, with reasons such as a domain that imitates a vendor's or a display name that does not match the address, beside its SPF, DKIM, ARC and DMARC results. A sender allowlist of vendor domains quarantines or rejects everyone else.
Match state on the thread
Invoice number, amount, PO match and approval state as typed metadata, validated on every write. Run the inbox at send_with_approval so every outgoing message is approved by a person.
Evidence for the auditors
The audit log records every change and every server decision with actor, key and outcome, exportable as JSON Lines. Mail exports as mbox or EML with metadata as JSON; retention policies delete or archive after your period, and a legal hold stops every deletion in its scope.
What does the code look like?
curl -X POST https://api.nofeb.com/v1/policy/lists -H "authorization: Bearer $NOFEB_API_KEY" \
-H 'content-type: application/json' \
-d '{"list": "sender_allow", "pattern": "vendor.example", "scope": "inbox", "inbox_id": "'$AP_INBOX'"}'
curl -X PUT https://api.nofeb.com/v1/policy/settings -H "authorization: Bearer $NOFEB_API_KEY" \
-H 'content-type: application/json' \
-d '{"scope": "inbox", "inbox_id": "'$AP_INBOX'", "settings": {"unlisted_sender": "quarantine"}}' // 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 does not pay invoices or connect to your ledger; your agent posts the extracted fields to the systems that do.
Frequently asked questions
How does an AP agent read invoice PDFs from email?
nofeb extracts each attachment's text and the invoice's key fields into metadata; the agent reads the fields, checks them against the text, and keeps the original for the record.
How do I catch spoofed vendor emails?
Receive on nofeb's MX: SPF, DKIM, ARC and DMARC are checked before acceptance, failures under a reject policy are refused, and every message carries a trust label that flags look-alike domains and display-name spoofing for your agent or rules to act on.
Can we keep AP mail for seven years and prove nobody deleted it?
Set a retention policy on the AP inbox for your period, add a legal hold when a case needs everything kept, and use the audit log, which records every delete and every policy change with who made it.
Is stored mail encrypted per customer?
Yes. Stored mail and metadata are sealed with keys derived per tenant, and deleting a tenant's keys makes its data unreadable.
Status of everything on this page
Every capability named above, with its status as reconciled against the engine.
| Capability | What it does | Status |
|---|---|---|
| Attachment text | Attachments are listed with their extracted text and can be downloaded byte-exact. | Shipped |
| Built-in and custom extractors | Receipts and orders, invoices (account numbers masked), calendar invitations and named entities extracted into typed metadata as mail arrives, plus your own extraction schemas run on your own model key, with the output validated against the schema. | Shipped |
| Byte-exact raw messages | Download any stored message exactly as it was received. | Shipped |
| Inbound mail server that checks mail at the door | nofeb's own MX receives mail for the shared domain and your custom domains, with STARTTLS. It checks every recipient before accepting any data, verifies SPF, DKIM, ARC and DMARC, and scans for spam and viruses before it answers. Mail that fails a DMARC reject policy, carries a virus or is clearly spam is refused during delivery instead of bounced later; likely spam and DMARC-quarantined mail is filed into Junk. Every message carries a security verdict with its authentication, spam, virus and TLS results. | Shipped |
| Sender trust on every message | Each inbound message is labelled trusted, known, unknown or suspicious, with the reasons: its authentication results, your sender lists, look-alike domains, display-name spoofing, and whether the inbox has corresponded with the sender before. | 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 |
| 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 |
| 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 |
| Append-only audit log | Every change made through the API, MCP or the console, and every hold, denial, rejection and approval the server makes on its own, recorded with the actor, key, operation, target, outcome and request id. Query it with filters and cursors, or export it as JSON Lines. | Shipped |
| Full export | A whole inbox, a folder, a thread or a search as mbox or a zip of EML files, with every message's folders, keywords, metadata and decisions as JSON, built in the background and downloaded through signed links. | Shipped |
| Retention policies and legal holds | Delete messages older than a number of days, or move them to Trash or Archive, per organization, pod, inbox or folder, keeping flagged mail by default, with a dry run that shows what a policy would do. A legal hold blocks every deletion in its scope, including expiry and inbox deletion. | Shipped |
| Per-tenant encryption with crypto-shredding | Stored mail and metadata are sealed with keys derived per tenant; deleting a tenant's key material makes its data unreadable. | Shipped |