Docs / Glossary

Glossary

The words we use, in plain language. Each term has its own link, so you can point someone at one.

Accountable person
The human who answers for an organization's agents. They own the rules, approve what needs approval, and alone can promote an agent's autonomy.
Agent
Software that uses an artificial intelligence (AI) model to read and write on someone's behalf. On Envolt Mail every agent has its own address, label and signing identity.
Agent Seal
A signed email header (Envolt-Agent-Seal) that says which agent sent a message, who it works for and how much autonomy it had. Anyone can verify it with the organization's published keys. See the format.
Airlock
Where every inbound message is parsed in isolation, turned into plain text, stripped of hidden content and stored encrypted, before anything reads it.
Anchor
A daily fingerprint of the whole ledger. Once anchored, history can't be rewritten without the change showing.
ASCII smuggling
Hiding text in Unicode tag characters, which render as nothing for people but are read by models. The Airlock removes and counts them.
Single-use capability
A short-lived, one-time permission to send one approved message. Agents never hold a standing key to send.
Case
One inbound message, described in a structured way: intent, urgency, summary, and any commitments or decisions in it.
Console
Where the accountable person works: the morning brief, the queue of decision cards, and the kill switch. A read-only preview runs in staging; see the tour.
Courier
Our name for an agent that works inside Envolt Mail. A Courier reads, sorts and drafts for one persona, and can send only what the Seal policy and the Director allow.
Decision card
One decision, ready to make: the ask in one line, a recommendation, two alternatives, the risk, the evidence and a deadline, with one-tap approve, edit, hold or delegate.
Director
Our name for the accountable person: the human who answers for what an organization's agents send. The console and the kill switch belong to the Director.
Disclosure
The plain-language lines that close every agent message: it was written by an agent, for whom, and how to reach a person.
Earned autonomy
Levels from L0 (observe only) to L4 (narrow, audited autonomy). An agent moves up only with a person's approval, backed by its measured record, and drops back automatically when it gets something seriously wrong.
Ledger
The tamper-evident record of everything that happens. Each event is chained to the one before it by a hash, so a missing or altered event breaks the chain.
Morning brief
A short daily summary for the accountable person: decisions waiting, promises coming due and anything unusual, readable in under three minutes.
Persona
A separate identity mail is handled for: a studio, a pen name, a stage name or a single project. Each persona is its own room, and nothing crosses between rooms unless you link them.
Prompt injection
Instructions planted in content to manipulate an AI system. In Envolt Mail, mail is data: nothing in it can change what an agent may do.
Quarantined reader
The model step that describes a message. It has no tools, sees redacted text, can only add warnings, and fails closed to a person.
Receipt
A public page behind each message's verify link: who the agent is, who it works for, whether a person approved. Never the content or recipients.
Seal policy
The policy engine every agent plan must pass: recipients, content, rate limits and approval rules your team owns. Not to be confused with the Agent Seal header.
Trust tier
How much a sender has been verified, from unknown to known contact. It changes how carefully a message is handled, never what an agent is allowed to do.