Settingsintermediate

Capability security levels

The enforcement level behind a capability's action tier — 0 (no proof), 2 (verified customer) or 3 (signed-in customer) — how identity verification unlocks it, and how response redaction works.

4 min read

Capability security levels

The security level is the enforcement integer every runtime gate reads. You no longer set it directly on a capability: you pick an action tier (Public / Read / Act / Transact) and the level is derived from the tier and from what the capability’s connection can actually ask a customer for. See Capability tiers and verification posture for the tier side of it.

The levels that exist

  • 0 — No proof — Open to anyone. No identity gate at all. — The Public tier.
  • 2 — Verified customer — A code sent to a channel already on the customer’s account. — Read or Act on a connection Atender can make a scoped call on once the customer id is fixed — an API-key connection, say.
  • 3 — Signed-in customer — The customer signed in on the connected system. — Transact, and Read or Act on a connection whose only credential is the customer’s own login (a customer-login endpoint, an External OAuth connection with an authorize URL and client ID, or a per-customer MCP session key).

There is no level 1. It is retired: nothing at runtime grants it, so a capability stored on it could never be unlocked by anybody. Rows written before it was retired still carry it — the agent’s capabilities tab renders those as “Legacy level 1 — retired. Not open to anyone: only a verified or signed-in customer clears it.” Public API create and update calls accept only 0, 2, and 3 and return a validation error for 1; first-party and session capability writes still map a submitted 1 to 2 for older client compatibility.

There is no supervisor-approval level. Nothing in the capability path pauses an action for a colleague to approve.

Successful capability and tool results can appear in agent debug with size caps and redaction applied; oversized responses are surfaced as tool errors instead of failing silently.

The stored default for a new capability is level 0, and re-deriving after a connection change can only ever raise a capability’s level, never lower it.

A specialist’s Capabilities tab can override the level per assignment — the choices are the same three, No proof / Verified customer / Signed-in customer. One floor applies: a capability that already requires a connection sign-in cannot be overridden below 3, because the execute-time gate reads the blueprint level and a lower override would bind a tool that then rejects every call it makes.

Voice agents execute only level 0 capabilities in the default configuration: the call’s tool binding is capped at L0, because without caller verification a gated tool could only be executed for “whoever dialled the number”. Where caller verification is enabled for the workspace, verify_caller (or, where Verify with BankID or MitID is also on, send_eid_link, a text-message link) lifts that cap and level 2 becomes reachable mid-call — but Transact never does: it is dropped from the call’s tool list and reported as human-only.

Identity verification

The level is the identity gate: it decides whether the capability is bound to the agent at all. There is no separate per-capability list of identity questions — the old identity-fields editor (email / order number / zip code answers matched against your records) was removed along with the L0–L3 radio, and its only writer is gone. What unlocks a level today is one of these mechanisms:

  • A one-time code, for level 2, sent to a channel already on the customer’s account — or, on a connection whose account lookup sets Where the code goes to To the email the customer gives, to that email once the lookup finds an account for exactly that address.
  • A proven email, for level 2, on an email conversation only. It is off by default and enabled per workspace. An email that is DKIM-signed by the sender’s own mail domain, or that replies to a message Atender sent in the thread, counts as verified with no code. On a connection whose code goes To the email the customer gives, it also confirms the account that address matches.
  • A trusted sign-in email, for level 2: when a signed-in web chat visitor’s email (see Trust the sign-in email in Capability authentication options) matches the lookup on such a connection, that account is confirmed with no code.
  • A national eID (BankID or MitID), for level 2. It is off until it is enabled for your workspace; once it is, an admin turns on Verify with BankID or MitID under Settings → Verification, and it works only on a connection whose account lookup fills Name field on that person and Birth date field on that person. It unlocks the account only when the signed-in person matches the holder, and a sign-in alone raises no level.
  • A sign-in on the connection, for level 3 — the customer-login endpoint, the External OAuth flow, or a minted per-customer MCP session key.

A code requested on an email conversation stays valid for 30 minutes. Codes on chat and SMS keep a 5-minute lifetime.

Level 2 capabilities can use an OTP step-up flow. On the web chat widget the customer sees an OTP card (unless a connection binds an account, in which case the widget steps up through the code tool instead): the agent never asks where to send the code — the widget collects any detail it needs, such as which email to use, then sends and checks the code.

Other surfaces do not render the OTP card. Email, SMS, WhatsApp/Messenger, Slack, Testing, and agent inbox/debug surfaces strip or preserve the verification marker safely instead of showing a raw __verification_code_required__ token to the customer or agent. On email, that means no card is shown, but a code requested on the conversation is still valid for the 30 minutes described above.

If an L2 tool is withheld because of an OAuth token or login gate, Atender uses the login path instead of OTP. Level 3 — the top level — remains login/full-auth only.

When a capability is available to the agent, verification has already succeeded and the agent should call the capability directly. When verification is still required, Atender withholds the tool and drives the appropriate verification or login flow instead of having the agent ask for passwords, forms, or auth tokens.

Redaction rules

Redaction masks fields in the response a capability gets back, before that response enters the AI’s context. It is set per capability and per connection, and it works on field paths, not on free-text patterns you write:

  • A rule is a simplified dot-path plus a replacement — $.customer.ssn → [REDACTED].
  • You can add extra field names to mask, matched case-insensitively anywhere in the response.
  • On top of that, a built-in default pass masks well-known sensitive field names (ssn, card_number, cvv, password, routing_number, passport_number, and similar) and two value patterns — an SSN-shaped string and a 16-digit card number.

There is no rule set for capability inputs, though the same rules also mask the arguments recorded on an execution. The AI sees the masked form.

How they combine

The tier, the connection’s sign-in method, and the redaction rules are independent dials. A high-stakes capability typically looks like:

  • Auth: OAuth2 + External OAuth
  • Action tier: Transact (derives level 3, signed-in customer)
  • Redaction rules: card number, full bank details

That capability won’t be offered to the agent at all until the customer has signed in on the connection, it is never bound on a voice call, and sensitive response fields are masked before the model sees them.

See also

Tags

Ai FeaturesReference