
Building a recipient allowlist for an email agent
A recipient allowlist limits who an email agent may send to on its own. Start with people already in the thread, then narrow to named addresses or domains.
5 min read
Blog · AI & email
AI triage, summaries, drafting and assistants that work with your mail, and how to keep a human in charge of every send.

A recipient allowlist limits who an email agent may send to on its own. Start with people already in the thread, then narrow to named addresses or domains.
5 min read

After an AI agent sends a bad reply, read two records: the activity feed for what it did and the audit log for who changed its setup. Here is the order.
6 min read

Quiet hours are a daily window when an email agent will not send on its own. Set them from when your team can review, in the mailbox timezone.
7 min read

Pick an email agent's daily send cap from your own data: run in Suggest first, count replies you approve unchanged, then set the cap just above a normal day.
5 min read

Two email agents can reply to each other forever. Stop it with Auto-Submitted checks, one reply per thread, a daily cap and a duplicate hold. A practical list.
6 min read

A good approval step shows the recipients, the full message, why the agent wrote it and what it is based on, and it expires if nobody acts. A checklist.
6 min read

Give an AI agent its own address on your domain, not your inbox login: a scoped key, a sender allowlist and human approval. Here is what breaks without them.
6 min read

Yes, if it only proposes and you approve: let an AI list newsletters and flag risky links, but click unsubscribe yourself on senders you know and signed up for.
5 min read

Starred, unassigned, mentions, waiting for a reply, cold pitches, one address, a date range, big files: eight read-only questions an assistant can answer.
5 min read

Should an AI give you a few short reply options or a full draft? How to choose the right level of help by message type, risk and how much you trust your review.
6 min read

Customers increasingly ask whether a person or a machine wrote the reply. What to disclose, where to say it and plain wording you can adapt for support email.
7 min read

AI can list who owes what after a long thread, but it also invents tasks and misses hidden ones. A reliable prompt, a checking routine and what to keep human.
5 min read