Standard
  • Docs
  • Examples
  • Pricing
  • About

Get started

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

Build

  • Examples
  • Operation profiles
  • Integration reference

Concepts

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

Security

  • Security model
Documentation menu

Get started

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

Build

  • Examples
  • Operation profiles
  • Integration reference

Concepts

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

Security

  • Security model
Standard

Managed confidential execution for sensitive 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
    • How Standard works
    • Run your first task
    • Connect
    • Join a Space

    Build

    • Examples
    • Operation profiles
    • Integration reference

    Concepts

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

    Security

    • Security model

    Get started

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

    Build

    • Examples
    • Operation profiles
    • Integration reference

    Concepts

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

    Security

    • Security model

    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 a receiving system can check against its own accepted policy. 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. Execution evidence does not establish that source records are truthful or complete.

    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.

    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.

    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.

    PreviousResults and lifecycleNextFollow-on tasks

    On this page

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

    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 recipient applies its own accepted references. 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.