FAQ

Questions and answers

Short answers to what people ask most. Something missing? Ask us.

Can I use Envolt Mail today?

Not yet. It is in development: agent mailboxes on our own domains receive mail in shadow, and everything else runs in our staging environment on synthetic test mail. Request early access and see what runs today.

Does it replace Gmail, Outlook or my mail server?

No. Envolt Mail is designed to sit beside the mail your people already use, never in its delivery path. It never takes over the mail exchanger (MX) records your people rely on, so if Envolt Mail is ever down, their mail still flows.

Can an agent send email on its own?

Not by default. Agents propose plans; the Seal policy checks each one, and a person approves. An agent can earn routine sends over time, and lose them just as fast (how). In staging the send path ends in a sink that sends nothing. The only real mail so far is a test delivery from one of our agent mailboxes to another.

How will people know a message came from an agent?

From the sender name, a closing disclosure, a signed Agent Seal header and a public receipt. See recognizing an Envolt Mail agent.

What stops a stranger from emailing my agent instructions?

Mail is treated as data, never as instructions. The Airlock strips what a person couldn't see before anything reads a message, and nothing in an email can raise an agent's permissions. Try to get past it in the Lab.

Is there a demo?

Yes. The Lab runs our real Airlock, Agent Seal verifier and ledger checks in your browser, and the console tour shows what the person in charge will see, on made-up data.

How is this different from giving an agent a shared inbox?

A shared inbox gives the agent a password and every power that comes with it. Envolt Mail gives it a labeled identity, a quarantined view of mail and no standing right to send. See the comparison.

Which artificial intelligence (AI) models does it use?

The reader is built for a small, fast Claude model, and that model is switched off. Today a no-cost synthetic stand-in runs in staging, so no mail reaches any model provider.

Is my mail used to train AI models?

Envolt Mail does not train models. The service's full privacy terms will be published before anyone can use it.

What will it cost?

Prices are not set yet. The rules they will follow are on the pricing page: free while it only reads, priced per accountable person, and model costs passed through at cost under a cap you can see.

Can AI agents read this website?

Yes. Every page is also published as Markdown (add .md to the path, or send Accept: text/markdown), with llms.txt, agents.json and a small read-only MCP server.

Who builds it?

VaultSpark Studios. Read more about us.

How do I report a security issue?

Email security@vaultsparkstudios.com. The disclosure policy says what's in scope and what to expect.