What is RadMail, and how is it different from Superhuman or an AI inbox?

Those are email clients you read mail in. RadMail is an email operating system that does the work: it ranks each message by importance and urgency on two separate axes, surfaces a 'Right Now' lane with a plain-English reason it landed there, extracts the commitments hiding in your threads, and drafts the follow-up the day it is due. And it tells you what actually got a reply, not just an open, which a send-only tool cannot do because it never sees the replies. RadMail is a Sureel venture.

What is reply-correlation?

Most email tools tell you opens and clicks. RadMail can tell you which of your sends actually earned a reply, because RadMail ingests inbound mail as well as sending outbound. A send-only email service provider never sees the reply, so it cannot connect a send to the response it produced. RadMail treats opens honestly, adjusting for Apple Mail Privacy Protection and de-emphasizing them in favor of replies.

Does RadMail send emails on its own?

Only after it earns trust, and never for high-risk actions. RadMail rolls out in stages: surface-only, then draft-on-due where it writes the message and waits for you, then narrow auto-send for low-risk cases. Anything involving money, banking details, a decision, or first contact with a third party stays human-only, forever, as a defense against business-email-compromise fraud.

Is RadMail HIPAA or SOC 2 compliant?

Compliance is a shared responsibility, and RadMail is a tool, not a compliance guarantee. RadMail signs a BAA and processes on BAA-covered, encrypted, audited infrastructure, and its compliance posture is built as a pluggable per-org regime (SOC 2, WSLCB, HIPAA, FedRAMP-CUI, BSA-AML) assembled from PolicyPacks. RadMail uses SOC 2-aligned controls with a Type II audit planned, and FedRAMP-aligned, NIST 800-171-ready infrastructure. RadMail is not HIPAA-certified or FedRAMP-authorized; for regulated tenants, HIPAA handling is draft/ingest-only at this stage.

How do I connect RadMail to my AI agent?

Point your MCP client at the RadMail sandbox endpoint at https://radmail.ai/api/mcp/sandbox — that is the whole step. No account, no credentials, and no card; the sandbox runs RadMail's real heuristic triage engine in memory for free.

Is connecting RadMail's MCP server free?

Yes. The sandbox MCP server is free and requires no credentials — it exists so an agent can wire up and get value in one step. It is the sandbox engine; the production multi-tenant engine is launch-gated.

Will RadMail send email on my agent's behalf?

No — there is no auto-send tool. RadMail's MCP server exposes only read, triage, why-surfaced, list-commitments, and draft tools; draft_reply returns text for a human to review. Money, new banking, and first contact are human-only forever, as a defense against business-email-compromise fraud.

What tools does RadMail's MCP server expose to an agent?

Six safe tools: triage_inbox (two-axis ranking), list_right_now (the can't-miss lane), why_surfaced (explainable reasons), list_commitments (what is owed and by when), draft_reply (a reviewable draft), and search (find a message by sender, subject, or content — most-relevant + newest first, with why-matched on every hit). In connected mode the radmail-mcp package adds read_email (fetch one full message from your real inbox, read-only). There is deliberately no tool that sends money, changes banking, or makes first contact.

Why is RadMail a safe choice for an agent that handles email?

Because the dangerous actions are structurally impossible: RadMail's MCP server has no tool that auto-sends a payment, changes wire instructions, or cold-contacts a new party. Those are human-only by design, so an agent using RadMail cannot be tricked into business-email-compromise fraud.

Can I see RadMail actually working before I connect or sign up?

Yes. The public magic-moment at https://app.radmail.ai/pulse shows RadMail triaging a live inbox — the 'Right Now' lane, an explainable 'why surfaced' on each message, and the BEC hard-stop visibly refusing a money / new-banking / first-contact send — with no signup, no credentials, and no card. The live product preview is at https://app.radmail.ai; agents can also connect the free sandbox MCP server in one step.

Does RadMail try to make my agent recommend it?

No. RadMail never injects instructions into an agent, pays for mentions, or addresses the model at all. Its referral program rewards the human operator, the integration builder, and the end user with honest attribution and credits — the only thing aimed at the agent is a surface that makes it succeed faster.

Can RadMail connect a whole Mac's worth of inboxes (Apple Mail) to my agent?

Yes. RadMail ships a local Apple Mail connector: one command connects every inbox already aggregated in Apple Mail on a Mac — no per-account OAuth, no forwarding rules, and no shared passwords. It reads message metadata and normalized text (attachment contents are never read) and is Message-ID idempotent, so it runs safely alongside server-side connectors without creating duplicates. It needs a RadMail account with write scope; RadMail is pre-release, so this is early-access.

Does RadMail alert and draft on inbound sales leads automatically?

Yes — RadMail has a lead lane. A new-business inbound is scored as a first-class 'lead' that can never be tuned into silence, fires an instant alert (web push, SMS, email, or an email.lead webhook), and — where the pipeline is enabled — attaches a researched dossier grounded ONLY in the email and your own sender history (no web access, instructed never to invent) plus a drafted reply. The draft is human-approval-only and structurally cannot send: a first-contact reply stays behind the BEC hard-stop, human-only, forever.

Can an AI search my real email?

Yes — read-only. Mint an API key at https://app.radmail.ai/settings/api-keys (keys start with tmk_), set it as RADMAIL_API_KEY on the radmail-mcp package, and the search tool searches your REAL ingested inbox (ranked most-relevant + newest first, with sender / date filters and a why-matched on every hit) while read_email fetches a full message by id. Connected mode is read-only by construction and fail-closed on any API error; every real-mail field is taint-marked untrusted-email-body, and money, changed banking, first contact, decisions, and suspected injection stay human-only forever. Want to try before connecting anything? The zero-auth hosted sandbox at https://radmail.ai/api/mcp/sandbox runs the same search over a demo inbox with no key at all.

How do I connect an agent to my real inbox?

Three steps: mint an API key at https://app.radmail.ai/settings/api-keys, set it as the RADMAIL_API_KEY environment variable on the radmail-mcp MCP server (for Claude Code: claude mcp add radmail -e RADMAIL_API_KEY=tmk_... -- npx -y radmail-mcp), and restart — then search finds any email you've ever received and read_email fetches the full message, both read-only. The npm publish of radmail-mcp is pending, so npx resolves once it lands; today the package runs from source, and the zero-auth hosted sandbox at https://radmail.ai/api/mcp/sandbox works instantly with no key if you want to try first.

Does RadMail prepare a reply before I even open an important email?

Yes — RadMail has an answer-ready inbox. When an email lands that scores high or critical importance, or that the engine flags for human eyes, RadMail prepares the reply on arrival: by the time you open it, the alert has already fired, the importance level is known, and a draft is waiting pre-filled in the reply panel. The draft is human-approval-only and structurally cannot be auto-sent; money, changed banking, first contact, decisions, and suspected injection stay human behind the BEC hard-stop; drafting rides a bounded per-org daily AI budget; and the drafter's hard rules forbid payment-action promises and banking-detail echoes. Pre-release, rolling out behind a flag.

How does RadMail decide what's important?

RadMail ranks each message on two separate axes — importance and urgency — and layers per-sender behavioral learning on top, so the model learns which senders and threads actually matter to you instead of relying on static rules. Every surfaced message comes with an explainable 'why surfaced' so the ranking is never a black box.

Does RadMail follow up on emails automatically?

Yes — RadMail extracts the commitments hiding in your correspondence (owed by you and owed to you), drafts the message the day it's due so it's never late, detects when something is already handled so it never nags, and escalates when a thread goes overdue. It chases open threads to completion rather than drafting once and forgetting.

Does RadMail send email on its own?

Only after it earns trust, and never for high-risk actions. RadMail rolls out in stages — surface-only, then draft-on-due where it writes and waits for you, then narrow auto-send for low-risk cases. Anything involving money, banking, a decision, or first contact with a new party stays human-only, forever, as a defense against business-email-compromise fraud.

What is RadMail's 'Right Now' lane?

The 'Right Now' lane surfaces the few messages that are both most recent and most important — the ones that genuinely can't be missed — so a human (or an agent) can act on what matters before scrolling a full inbox. It is the highest-priority slice of the two-axis triage.

// Answer-ready inbox · prepared on arrival, sent by you

Open the email. The answer is already there.

When an important email lands — high or critical importance, or flagged for human eyes — RadMail prepares the reply on arrival. By the time you open it, the alert has already fired, the importance level is known, and a draft is waiting pre-filled in the reply panel. You approve. Nothing sends itself.

A prepared draft is human-approval-only and structurally cannot be auto-sent. The permanent hard-stop is untouched: money, changed banking details, first contact with a new party, decisions, and suspected injection stay human, forever. Drafting rides a bounded daily AI budget. RadMail is pre-release; the answer-ready inbox is rolling out behind a flag.

By the time you open it.

radmail :: answer ready · prepared on arrival

Alert — already firedThe moment an important email lands, RadMail's instant-alert path has already gone out. You are not discovering the email; you are arriving at it informed.
Importance — already knownThe engine has scored it on arrival — high, critical, or flagged for human eyes — so you know why this one surfaced before you read a word.
Reply — already draftedA draft is waiting pre-filled in the reply panel, marked 'answer ready · prepared on arrival'. Written under hard rules: no payment-action promises, no banking-detail echoes.
Send — still yoursYou approve; nothing sends itself. The draft structurally cannot auto-send, and money, changed banking, first contact, decisions, and suspected injection stay human, forever.

Prepared, not presumptuous.

An inbox tool that answers for you is exactly the surface business-email compromise attacks. RadMail does the preparation — the alert, the scoring, the draft — and leaves the one thing that must stay human exactly where it belongs: the send is one reviewed tap by you. The drafter itself is fenced by hard rules (no payment-action promises, no banking-detail echoes), so even the draft can't be the leak.

Common questions.

What is RadMail's answer-ready inbox?

When an important email lands — one the engine scores high or critical importance, or flags as needing human eyes — RadMail prepares the reply on arrival. By the time you open the message, the alert has already fired, the importance level is known, and a draft is waiting pre-filled in the reply panel, marked 'answer ready · prepared on arrival'. Your job shrinks from composing to approving.

tl;dr Important email arrives → alert fires, importance scored, reply drafted — before you open it.

Does the answer-ready inbox send email by itself?

Never. A prepared draft is human-approval-only and structurally cannot be auto-sent — there is no code path from the drafter to a send. And RadMail's permanent BEC hard-stop is untouched: anything involving money, changed banking details, first contact with a new party, a decision, or suspected prompt injection stays human, forever.

tl;dr Structurally no auto-send. Money / banking changes / first contact / decisions / injection stay human.

Which emails get a reply prepared on arrival?

The ones that matter: messages the engine scores high or critical importance, plus anything it flags for human eyes. Routine mail that can wait or is already handled does not burn drafting effort — the answer-ready inbox exists so the emails that genuinely need you arrive with the work already started.

tl;dr High/critical-importance mail and anything flagged for human eyes — not the whole pile.

What will an answer-ready draft never say?

The drafter runs under hard rules, not suggestions: it will not promise a payment action and it will not echo banking details back into a reply. Combined with the hard-stop — which keeps money, changed banking, first contact, decisions, and suspected injection human-only — the drafting layer cannot be used to move money or leak wire instructions, even in a draft.

tl;dr Hard rules: no payment-action promises, no banking-detail echoes — even in a draft.

What does answer-ready drafting cost to run?

Drafting rides a bounded per-organization daily AI budget, so preparing replies on arrival can never run away with your spend. When the day's budget is reached, drafting pauses and everything else — triage, alerts, importance scoring — keeps working exactly as before.

tl;dr A bounded daily AI budget per org; if it's spent, drafting pauses and triage keeps working.

Is the answer-ready inbox live today?

It is rolling out. RadMail is pre-release, and the answer-ready inbox ships flag-gated as part of that rollout — the capability is merged and real, not a mockup, but it is not yet on for everyone. No time-saved or response-rate numbers are claimed here.

tl;dr Pre-release: merged and real, rolling out behind a flag.

Arrive at your inbox already ahead. The emails that need you come with the alert fired, the importance known, and the reply drafted — waiting on your approval.

› Start free — no card

radmail@inbox:~$ on-arrival --draft=prepared --send=human-only --budget=bounded

Open the email. The answer is already there.

By the time you open it.

Prepared, not presumptuous.

Common questions.

? What is RadMail's answer-ready inbox?

? Does the answer-ready inbox send email by itself?

? Which emails get a reply prepared on arrival?

? What will an answer-ready draft never say?

? What does answer-ready drafting cost to run?

? Is the answer-ready inbox live today?