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

    Verification checks

    The evidence reference: each check the receiving client runs automatically, the references it uses and where it runs, for integrators and auditors.

    Standard Proof is execution evidence that the receiving integration verifies against its own accepted policy before it uses a result. The receiving client runs these checks automatically before it delivers a result, so the next agent can use it without manual inspection. This page lists the checks for integration testing, auditing and troubleshooting.

    Input bindings identify the artifacts or snapshots used. Source provenance is covered only when the operation includes evidence of the source. Recipients evaluate source content under their own acceptance policy.

    Where verification runs

    The recipient's integration, SDK, or verification software checks the evidence in an environment it trusts. A dashboard status or an agent's success message is not a substitute for those checks.

    Configure the dependent action to require successful verification. Displaying a proof status to the model does not enforce that requirement.

    The same requirements apply when the same agent continues its own work, not only when one agent hands work to another. An agent that requested an operation and then acts on its result still proceeds only through an integration that verifies Standard Proof, evaluates the result and enforces authority for the next action.

    Accepted references must be established independently of the candidate result. They include the runtime identity and revocation state, evidence-signing trust roots, workload and input digests, applicable authority, and the recipient's verification policy.

    Claims to check

    The required evidence depends on the selected operation and execution boundary.

    ClaimRequired relationship
    RuntimeAttestation must match the accepted environment and applicable freshness or revocation requirements.
    WorkloadThe recorded workload must match the approved code, model, or verifier.
    InputsRecorded input bindings must match the expected artifacts or snapshots.
    AuthorityThe operation and release must be covered by the required permissions.
    ResultThe evidence must bind to the exact returned result and intended release context.
    SignatureThe signed evidence must validate under the accepted trust model.

    Missing evidence for a required claim is a verification failure. A claim outside the recorded boundary remains unverified. Cleanup is reported separately and is not proof of physical erasure.

    Conversation analytics outcomes

    The Conversation analytics example distinguishes four outcomes: counts ready, an input check failed, publication held, and invalid evidence. Duplicate conversation IDs are checked by the example function. An accepted failure report contains no category counts; it is not a successful classification.

    PreviousResults and lifecycleNextFollow-on tasks

    On this page

    • Where verification runs
    • Claims to check
    • Conversation analytics outcomes
    • Independent checks for agent-written code
    • From verification to action
    • Evidence across systems

    The receiving integration must verify the permitted result itself. Hosted operation or delivery metadata does not establish that verification. Execution evidence does not certify classification accuracy or the truth of the source conversations.

    Independent checks for agent-written code

    Pin the test suite, evaluator, and acceptance policy outside the producing agent's authority. Verify their digests as well as the candidate artifact's digest. A different test suite cannot silently satisfy a policy that requires the original suite.

    This establishes which checks ran and their recorded outcomes. It does not establish that the tests are sufficient or that the software has no defects.

    From verification to action

    An accepted proof may contain a failing security report. Verify the evidence first, evaluate the report second, and enforce authority for the next action separately. For release, all three must succeed before the exact tested artifact proceeds.

    A valid proof is not an authorization token for the next action. The receiving system needs its own authority for that.

    Keep these outcomes distinct:

    • Failed check. The evidence is valid and shows that the result did not meet a required check.
    • Invalid or mismatched proof. A signature, digest or reference does not match, so nothing in the record is used.
    • Missing owner authorization. A required owner did not authorize the use, so the operation does not run.
    • Release refused. The computation finished, but a required owner withheld release, so the result does not reach that recipient.

    Evidence across systems

    Authorized recipients can pass evidence to another agent or verifier, subject to disclosure rules. Each receiving integration verifies the evidence against its own accepted references before use. It does not need to rely on the producing agent's account of the execution.

    For external tools, the evidence covers only the authorized request, observed response, or other claims actually bound within Standard's boundary. It does not attest the tool provider's internal execution.

    See Security model for the trust assumptions and limits.