Standard
  • Docs
  • Examples
  • Pricing
  • About

Get started

  • Overview
  • Conversation analytics
  • How Standard works
  • Run your first task
  • Connect
  • Join a Space

Build

  • Authoring · Sales calculation
  • Examples
  • Software release verification
  • Operation profiles
  • Integration reference

Concepts

  • Sources and customer vaults
  • Inputs and permissions
  • Accounts and billing
  • Results and lifecycle
  • Verification checks
  • Follow-on tasks
  • Cleanup

Security

  • Security model
  • Threat model and AI risk mapping
Documentation menu

Get started

  • Overview
  • Conversation analytics
  • How Standard works
  • Run your first task
  • Connect
  • Join a Space

Build

  • Authoring · Sales calculation
  • Examples
  • Software release verification
  • Operation profiles
  • Integration reference

Concepts

  • Sources and customer vaults
  • Inputs and permissions
  • Accounts and billing
  • Results and lifecycle
  • Verification checks
  • Follow-on tasks
  • Cleanup

Security

  • Security model
  • Threat model and AI risk mapping
Standard

Managed confidential execution for approved functions.

© 2026 Standard Runtime, Inc. All rights reserved.

  • Security
  • Docs
  • Examples
  • Pricing
  • FAQ
  • About
  • Contact
  • Terms
  • Privacy
  • Cookies
  • Docs
  • Examples
  • Pricing
  • About
  • Get started

    • Overview
    • Conversation analytics
    • How Standard works
    • Run your first task
    • Connect
    • Join a Space

    Build

    • Authoring · Sales calculation
    • Examples
    • Software release verification
    • Operation profiles
    • Integration reference

    Concepts

    • Sources and customer vaults
    • Inputs and permissions
    • Accounts and billing
    • Results and lifecycle
    • Verification checks
    • Follow-on tasks
    • Cleanup

    Security

    • Security model
    • Threat model and AI risk mapping

    Get started

    • Overview
    • Conversation analytics
    • How Standard works
    • Run your first task
    • Connect
    • Join a Space

    Build

    • Authoring · Sales calculation
    • Examples
    • Software release verification
    • Operation profiles
    • Integration reference

    Concepts

    • Sources and customer vaults
    • Inputs and permissions
    • Accounts and billing
    • Results and lifecycle
    • Verification checks
    • Follow-on tasks
    • Cleanup

    Security

    • Security model
    • Threat model and AI risk mapping

    Inputs and permissions

    How encrypted inputs and key access work, how each required owner authorizes independently, and how each operation is approved when it is requested.

    Agents need authority for the resources they use and the results they release. Standard binds those permissions to execution, whether the resources belong to one organization or several owners.

    Each required owner authorizes independently. One owner’s approval cannot replace another’s, and a sponsor or coordinator cannot approve on an owner’s behalf. Owners sign their approvals and release authorizations with keys they hold.

    In Conversation analytics, the conversation batch, classifier and reporting policy have distinct roles. The Analytics agent can request counts without gaining authority to change the classifier, expand the batch or choose another recipient.

    Choose an input route

    For local files, the participant host encrypts inputs before contribution to the accepted confidential runtime. For connected sources, the request identifies an approved connection and resource selection; attested confidential ingress retrieves and validates the material before sending it to the operation worker. Private contents stay out of agent conversations and ordinary tool arguments. See Sources and customer vaults for the complete flow.

    An encrypted-input reference identifies an object and its expected digest. Holding the reference does not grant permission to decrypt or use it. References can still contain sensitive metadata and should follow your disclosure policy.

    Key access and attestation

    The key-access policy determines which attested runtime and authorized execution may obtain decryption material. Required checks include the accepted runtime identity, workload, and applicable authority. If the required conditions are not met, the protected execution cannot use the input.

    Non-exportable vault/KMS master keys remain in the customer’s key store, where decrypt or sign operations use them. Transient data keys and permitted API secrets can be used in confidential memory. Customer-store policies govern access; provider-specific authentication and attestation conditions apply. Agent requests carry references rather than raw credentials.

    Code, models, and validation inputs

    Code and model artifacts can be protected inputs as well as data. They must match the runtime's supported formats and resource limits.

    Accept the classifier and its inputs under authority separate from the requesting agent. Hardware attestation alone does not establish classification accuracy. The accepted policy identifies the required function, batch and output; evidence binds the result to that operation. Independent checks of agent-written code are covered in the separate release-verification example.

    See Formats and limits.

    Permission scope

    PreviousSources and customer vaultsNextAccounts and billing

    On this page

    • Choose an input route
    • Key access and attestation
    • Code, models, and validation inputs
    • Permission scope
    • Source selection and approval
    • Per-operation approval
    • Independently owned resources
    • Related pages
    ScopeWhat it establishes
    CallerWhich identity may request the operation.
    WorkloadWhich approved code, model, or supported operation may run.
    ResourcesWhich inputs and capabilities the execution may use.
    ReleaseWhat result may leave and which recipients may receive it.

    Permission to run a computation does not automatically authorize disclosure of its inputs. Membership in a Space does not grant access to every resource in that Space.

    Source selection and approval

    Before retrieval, confidential ingress checks the approved connection, resource selection, version and required input bindings. After retrieval, it checks the bytes against the required digest and size. A mismatch is refused before the input reaches the approved function. Connection verification and approval-time snapshots have separate scoped permissions and can precede final operation approval.

    Per-operation approval

    By default, an owner approves each operation when it is requested, and the approval covers that operation only. A request to use a new verifier, expand resource access, or change the result recipient must satisfy each affected owner's policy before continuing.

    An owner can opt in, per host, to a standing permission: a passkey approval that lets one exact task repeat without a new approval. It covers the same inputs, recipients and release rule, never connected sources, and lasts at most 100 runs over at most 30 days. Standing permissions are off by default and revocable from the Space page; revocation takes effect when Standard records it, and until then runs continue within the remaining runs and expiry. An agent cannot change what a standing permission covers, and each other required owner still approves independently.

    When a policy reserves an authorization decision, the required authority must be supplied. Missing authority blocks the operation or release; an agent cannot broaden its own permissions. Authorization cannot turn invalid evidence into valid evidence.

    Independently owned resources

    A workflow can add another owner's data, software, or model when needed. Each owner retains control over its contribution and permitted release, and the operation runs only when every required owner has authorized it. This is the same permission model used within one organization, with more required authorities.

    Related pages

    • Accounts, Spaces and billing
    • Security model