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

    Security model

    How scoped authority, confidential ingress, protected execution and Standard Proof govern sensitive work.

    Standard combines execution integrity, scoped authority, and confidentiality for managed confidential execution. This page defines the protection boundaries and the assumptions behind Standard Proof.

    Zero-trust principles

    Standard separates requesting work from authorizing the use of inputs, execution of a function and release of results. Each operation must satisfy the applicable owner permissions, accepted workload and execution requirements.

    The receiving integration verifies Standard Proof against the expected operation and independently accepted references before accepting the result. Your workflow then evaluates the outcome and enforces permission for the next action, whether the same agent continues or another agent takes over.

    These checks rely on explicitly accepted hardware and attestation roots, approved software, secure keys and correctly configured verifiers.

    Customer-defined checks

    Customers implement required calculations, validations and failure behavior inside the approved function. Establish its accepted workload revision outside the requesting agent’s authority. The caller requests the function with authorized inputs; admission checks the workload and scope, and rejects substitutions.

    The function’s code determines its business result. Customer tests establish its intended behavior; Standard Proof binds the recorded execution to the accepted workload and inputs. A function can return a permitted report containing failed checks. The receiving integration verifies the evidence, evaluates that report and applies its own policy before a dependent action.

    Restricted Wasm execution

    The approved function runs as a Wasm module with declared input and output interfaces and resource limits. It reads only the inputs the operation declares, writes only declared output candidates and observes cancellation. It has no general shell, filesystem, subprocess or network interface, and it does not inherit the requesting agent’s filesystem, shell or credentials.

    Memory, fuel, duration and input and output sizes are bounded by the accepted limits. Ingress’s scoped permission to use a source credential is separate from the workload’s interfaces: connected-source retrieval happens in confidential ingress, and the function receives only validated inputs. Output candidates leave only as the release rules permit. See Write a protected function for the interface.

    Execution integrity

    Runtime attestation identifies the accepted execution environment. Execution evidence binds the relevant workload, authority, inputs, and result within that environment. A recipient verifies those bindings against references it accepts independently of the producing agent.

    Signed evidence is tamper-evident: changing signed contents must invalidate their verification. The strength of a claim depends on the evidence source, its binding to the result, and the accepted trust roots. A signature on an untrusted statement alone does not establish that the statement is true.

    PreviousCleanupNextThreat model and AI risk mapping

    On this page

    • Zero-trust principles
    • Customer-defined checks
    • Restricted Wasm execution
    • Execution integrity
    • Scoped authority and release
    • Confidentiality and customer custody
    • Questions customers ask
    • External tools and services
    • Metadata and operators
    • Workload and release configuration
    • Recipient verification

    For agent-written code, the verifier, tests, and acceptance policy must remain outside the producing agent's authority. An attested run of weakened tests is still a run of weakened tests. Check the accepted versions as well as the result.

    Scoped authority and release

    Standard enforces the applicable operation, resource, and release rules. Permission to execute does not automatically authorize additional disclosure or a downstream action. Each operation needs the current approval of each required owner, or that owner’s standing permission for that exact task (same inputs, recipients and release rule; no connected sources; at most 100 runs over at most 30 days). One owner’s standing permission never stands in for another owner’s approval; missing authority blocks the request or release.

    A Space can contain agents and resources within one organization or across independent owners. Each resource's policy still applies.

    Confidentiality and customer custody

    Local files are encrypted by the participant host before contribution. Connected-source requests name an approved connection and selection. Attested confidential ingress retrieves the material under scoped permission, validates required input bindings and contributes it through a protected session to the operation worker.

    Customers retain persistent control of keys and API secrets in their own vaults or key stores. Non-exportable master keys stay there; transient data keys and API secrets can be used in the appropriate confidential components. Customer-store authentication and attestation enforcement follow the configured provider’s supported policy.

    Before retrieval, ingress checks the connection, selection, version and required bindings. After retrieval, digest and size checks validate the bytes. Only validated inputs reach the approved function. Connection verification and approval-time snapshots can precede final operation approval under separate scoped permissions.

    Release rules select the permitted result and authorized recipient. The authorized Analytics integration can receive category counts while the underlying conversations and source credentials remain outside its process. See Sources and customer vaults.

    Questions customers ask

    Who speaks for each owner? An accepted, Standard-issued identity anchored to the participant's own signing keys, acting under bounded delegation. Delegations can be revoked, and authority must be current when it is used.

    Who can approve an operation? Each required owner, independently. Sponsoring a Space or inviting a participant does not transfer control of anyone's assets.

    Where is plaintext? At the owner’s source and preparation endpoints; inside attested confidential ingress and the operation worker as needed for permitted input retrieval and processing; and at authorized recipient endpoints after permitted outputs are decrypted there. A permitted output leaves the worker sealed to the recipient's key; the attested ingress and Standard's other services carry it only as ciphertext. Protected input contents stay out of routine coordination, agent prompts and operator-visible logs. Operational metadata remains outside this protected-input confidentiality claim.

    What can leave? Only results and recipients authorized by the applicable output contract and release authorizations. Execution success alone is not release permission.

    What can the next system verify? Signed, checkable evidence for the exact operation, under trust roots it accepted. Verification does not confer new permissions.

    External tools and services

    An ordinary API or MCP service remains outside Standard's attested execution boundary. Evidence can cover a supported request and the response observed by Standard. It cannot establish the external service's internal computation unless that computation has its own accepted evidence.

    Using an existing tool does not require its provider to join a Space or package its backend for Standard. When a workload needs confidential processing inside Standard, it must use a supported protected execution path.

    Metadata and operators

    Standard's coordination services process account, permission, status, and usage metadata. That metadata is distinct from the private contents protected by the confidential runtime. Protecting execution inputs does not make every aspect of service operation confidential.

    Workload and release configuration

    The approved function’s interfaces and limits are described under Restricted Wasm execution.

    Select accepted hardware and attestation roots, workload versions, signing identities and recipient verification references. Configure the release rules for the intended output form, recipients and repeated-query policy.

    Recipient verification

    Standard Proof binds supported runtime, workload, authority, input and result claims through the delivered verification contract. Input digests identify the bytes used. Internal source checks enforce approved retrieval; recipient verification of source claims uses authenticated source records included in the delivered contract.

    See Verification checks and the threat model and AI risk mapping.