> ## Documentation Index > Fetch the complete documentation index at: https://docs.effectiveai.app/llms.txt > Use this file to discover all available pages before exploring further. # Evaluate a program’s latest release > Evaluate the entry of a program’s latest release, as [Evaluate a program release](/api-reference/your-programs/evaluate-a-program-release) does: `inputs` for a rater entry, `commands` for a guideline entry. Without a version in the path, the call answers on the program’s latest release, resolved once; the response’s `releaseVersion` and `bundleId` name what answered. A new release changes what this operation answers. ## OpenAPI ````yaml /openapi.json post /rsl/{id}/evaluate openapi: 3.0.3 info: title: Effective API version: 2.0.0 description: The public Effective REST API. Authenticate using an Effective API key. servers: - url: https://api.effectiveai.app/api/v2 description: Production security: - bearerAuth: [] paths: /rsl/{id}/evaluate: post: tags: - Your programs summary: Evaluate a program’s latest release description: >- Evaluate the entry of a program’s latest release, as [Evaluate a program release](/api-reference/your-programs/evaluate-a-program-release) does: `inputs` for a rater entry, `commands` for a guideline entry. Without a version in the path, the call answers on the program’s latest release, resolved once; the response’s `releaseVersion` and `bundleId` name what answered. A new release changes what this operation answers. operationId: evaluateProgram parameters: - schema: type: string minLength: 1 maxLength: 128 pattern: ^[a-z0-9][a-z0-9._-]{0,127}$ description: >- Your organization’s ID for the program, chosen at its first upload: lowercase letters, digits, dots, underscores and hyphens. A rater’s program ID is its rater ID. required: true description: >- Your organization’s ID for the program, chosen at its first upload: lowercase letters, digits, dots, underscores and hyphens. A rater’s program ID is its rater ID. name: id in: path requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/V2ProgramRootEvaluateRequest' responses: '200': description: >- A rater entry: the result, timings and the exact release and bundle that answered. A guideline entry: the status after the commands, and the release and bundle that decided them. content: application/json: schema: $ref: '#/components/schemas/V2ProgramRootEvaluateResult' '400': description: >- Invalid request, or program_role_required: a guideline entry’s commands need a role, and the caller holds several and named none. content: application/json: schema: $ref: '#/components/schemas/V2CodedError' '401': description: Authentication required. content: application/json: schema: $ref: '#/components/schemas/V2CodedError' '403': description: >- The user permission is missing, or no_program_role: the caller holds no program role in this workspace, or not the one named; a guideline entry’s commands act in one. content: application/json: schema: $ref: '#/components/schemas/V2CodedError' '404': description: >- program_not_found, release_not_found, or alias_not_found: the release’s entry uses no rater by that alias. content: application/json: schema: $ref: '#/components/schemas/V2CodedError' '409': description: >- wrong_component: the release’s entry does not answer this call, for example `inputs` sent to a guideline entry’s evaluate; alias_unavailable: the release records no engine that calls its raters by alias; contract_unavailable: a rater entry has no stored contract. content: application/json: schema: $ref: '#/components/schemas/V2CodedError' '413': description: The inputs exceed 1 MiB. content: application/json: schema: $ref: '#/components/schemas/V2CodedError' '415': description: The request body is not application/json. content: application/json: schema: $ref: '#/components/schemas/V2CodedError' '422': description: >- invalid_inputs, business_rejection or evaluation_failed for a rater entry; command_refused for a guideline entry: `refusal` carries the engine’s code, message and candidates, as a log’s preview would. content: application/json: schema: $ref: '#/components/schemas/V2CodedError' '429': description: Too many requests, or rater_overloaded. Retry after Retry-After. content: application/json: schema: $ref: '#/components/schemas/V2CodedError' '500': description: Unexpected failure. content: application/json: schema: $ref: '#/components/schemas/V2CodedError' '503': description: >- rate_timeout, rater_unavailable or a dependency is unavailable. Retry after Retry-After. content: application/json: schema: $ref: '#/components/schemas/V2CodedError' security: - bearerAuth: [] components: schemas: V2ProgramRootEvaluateRequest: anyOf: - $ref: '#/components/schemas/V2ProgramEvaluateRequest' - $ref: '#/components/schemas/V2ProgramCommandsRequest' V2ProgramRootEvaluateResult: oneOf: - $ref: '#/components/schemas/V2ProgramEvaluateResult' - $ref: '#/components/schemas/V2ProgramGuidelineEvaluateResult' discriminator: propertyName: component mapping: rater: '#/components/schemas/V2ProgramEvaluateResult' guideline: '#/components/schemas/V2ProgramGuidelineEvaluateResult' V2CodedError: allOf: - $ref: '#/components/schemas/V2Error' - type: object properties: code: type: string minLength: 1 description: Stable error code. Clients must tolerate unknown future codes. details: type: array items: type: object properties: location: type: string enum: - path - query - header - body path: type: array items: type: string maxLength: 64 maxItems: 12 code: type: string enum: - required - invalid_type - invalid_value - unknown_field message: type: string minLength: 1 maxLength: 200 required: - location - path - code - message minItems: 1 maxItems: 20 description: Bounded safe validation issues; may omit some invalid fields. requestId: type: string minLength: 1 maxLength: 128 description: >- Existing server correlation for this HTTP attempt, when available. dataset: type: string enum: - naic - osha description: Dataset needed for dataset_not_enabled. businessCode: type: string description: The rater’s own refusal code, for business_rejection. violations: type: array items: type: object properties: code: type: string description: Authored or built-in constraint code message: type: string description: Authored message for the failed constraint path: type: string description: Input path of the offending value; empty for the request value: nullable: true description: Offending input value, size-bounded by the runtime constraint: type: string description: The constraint the value failed, as text cite: type: string nullable: true description: >- Filing citation of the constraint, when the source cites one required: - code - message - path - value - constraint - cite additionalProperties: false maxItems: 256 description: >- Each input constraint the submission failed, for invalid_inputs and business_rejection. violationsTruncated: type: boolean description: >- True when the rater reported more violations than violations holds. executionId: type: string description: >- The recorded execution of a failed rating, for rater rating failures. accessUrl: type: string nullable: true format: uri description: Not currently returned. required: - code V2ProgramEvaluateRequest: type: object properties: inputs: type: object additionalProperties: nullable: true description: >- Engine input: one key per root record, for example `{"Policy": {...}}`. detailed: type: boolean description: >- When true, return computed calculation values as well as declared outcomes. Omit or set false to return only what the contract’s outputSchema describes. required: - inputs additionalProperties: false V2ProgramCommandsRequest: type: object properties: commands: type: array items: oneOf: - type: object properties: kind: type: string enum: - answer question: type: string minLength: 1 maxLength: 500 description: >- An input’s path under the root record (policy.payroll), or a referral’s name for a sign-off. value: anyOf: - type: string - type: number - type: boolean - nullable: true - type: array items: nullable: true - type: object additionalProperties: nullable: true description: >- The answer, as the contract’s questions schema reads it. For a sign-off, Approved or Declined. from: type: string minLength: 1 maxLength: 2000 description: Where the answer comes from, such as a document page. because: type: string minLength: 1 maxLength: 2000 description: >- Why the actor gives it. A sign-off, and an answer to a question a role holds, need one (REASON_REQUIRED). option: type: string pattern: ^[A-Za-z_][A-Za-z0-9_]{0,63}$/u description: >- A quote option: the command writes in that option’s view. Omit for the shared answers. required: - kind - question - value additionalProperties: false - type: object properties: kind: type: string enum: - retract question: type: string minLength: 1 maxLength: 500 description: >- An input’s path under the root record (policy.payroll), or a referral’s name for a sign-off. option: type: string pattern: ^[A-Za-z_][A-Za-z0-9_]{0,63}$/u description: >- A quote option: the command writes in that option’s view. Omit for the shared answers. required: - kind - question additionalProperties: false - type: object properties: kind: type: string enum: - quote name: type: string pattern: ^[A-Za-z_][A-Za-z0-9_]{0,63}$/u description: A quote’s or quote option’s name, such as q1 or with_pl. option: type: string pattern: ^[A-Za-z_][A-Za-z0-9_]{0,63}$/u description: >- A quote option: the command writes in that option’s view. Omit for the shared answers. required: - kind - name additionalProperties: false - type: object properties: kind: type: string enum: - bind name: type: string pattern: ^[A-Za-z_][A-Za-z0-9_]{0,63}$/u description: A quote’s or quote option’s name, such as q1 or with_pl. required: - kind - name additionalProperties: false - type: object properties: kind: type: string enum: - close reason: type: string enum: - withdrawn - expired - lost - declined because: type: string minLength: 1 maxLength: 2000 required: - kind - reason additionalProperties: false minItems: 1 maxItems: 500 role: type: string pattern: ^[a-z_][a-z0-9_]{0,63}$/u description: >- The role to act in, for a caller who holds several on this guideline. Defaults to the only one held. required: - commands additionalProperties: false description: >- The commands to decide, as a log’s write takes them, and the role to act in. They are decided as a log just opened on the release would decide them, and nothing is kept. V2ProgramEvaluateResult: type: object properties: component: type: string enum: - rater description: 'A rater answered: the entry, or a used rater.' executionId: type: string description: ID of the saved execution. Failed ratings save one too. programId: type: string minLength: 1 maxLength: 128 pattern: ^[a-z0-9][a-z0-9._-]{0,127}$ description: >- Your organization’s ID for the program, chosen at its first upload: lowercase letters, digits, dots, underscores and hyphens. A rater’s program ID is its rater ID. releaseVersion: type: integer minimum: 0 exclusiveMinimum: true description: >- The release that answered. A call without a version answers on the latest. bundleId: type: string pattern: ^[a-f0-9]{64}$ description: SHA-256 identity of the bundle that answered. alias: type: string nullable: true description: >- The used rater that answered, by its alias; null when a rater entry answered. programFingerprint: type: string description: >- Fingerprint of the program that answered: the entry’s, or the used rater’s. lane: type: string enum: - worker - local description: >- Where the rating ran. `worker`: the Worker that runs the engine the bundle carries. `local`: the API’s own rslc engine. result: type: object additionalProperties: nullable: true description: >- Outputs keyed by root record. The contract’s outputSchema describes them. The engine computes in exact decimals; the API returns them as JSON numbers with 64-bit float precision, about 15 significant digits. timings: type: object properties: totalMs: type: number minimum: 0 coldStartMs: type: number minimum: 0 evaluateMs: type: number minimum: 0 workerMs: type: number minimum: 0 materializeMs: type: number minimum: 0 required: - totalMs - workerMs additionalProperties: false description: >- Milliseconds spent on this rating. coldStartMs is present only on a cold start. required: - component - executionId - programId - releaseVersion - bundleId - alias - programFingerprint - result - timings additionalProperties: false V2ProgramGuidelineEvaluateResult: type: object properties: component: type: string enum: - guideline description: The guideline entry answered. programId: type: string minLength: 1 maxLength: 128 pattern: ^[a-z0-9][a-z0-9._-]{0,127}$ description: >- Your organization’s ID for the program, chosen at its first upload: lowercase letters, digits, dots, underscores and hyphens. A rater’s program ID is its rater ID. releaseVersion: type: integer minimum: 0 exclusiveMinimum: true description: >- The release that answered. A call without a version answers on the latest. bundleId: type: string pattern: ^[a-f0-9]{64}$ description: SHA-256 identity of the bundle that answered. status: allOf: - $ref: '#/components/schemas/LogStatus' - description: >- The status after the commands: what a log opened on this release would report after them. Numbers as the program computed them. required: - component - programId - releaseVersion - bundleId - status additionalProperties: false V2Error: type: object properties: error: type: string minLength: 1 description: Human-readable explanation of the failure. required: - error LogStatus: type: object properties: stage: type: string enum: - Open - Ineligible - Declined - Quotable - Bound - Closed description: Where the submission stands. outcomes: type: object additionalProperties: nullable: true description: The rating outcomes; empty while any is unknown. unrated: type: array items: type: object properties: name: type: string description: The outcome’s or referral’s name. by: type: string description: The alias of the used program that declines. code: type: string description: The declining rule’s code. message: type: string required: - name - by - code - message description: >- Outcomes and referral conditions with no value because a program they read declines. declines: type: array items: type: object properties: code: type: string description: The rule’s code, or the referral’s name. message: type: string path: type: string cite: nullable: true description: A JSON value, as the program reads it. Numbers as written. required: - code - message - path description: Rules and sign-offs that decline. open: type: array items: type: object properties: question: type: string description: An input’s path, or a referral’s name. kind: type: string enum: - input - signoff role: type: string nullable: true description: The lowest role that may answer it. choices: nullable: true description: A JSON value, as the program reads it. Numbers as written. because: type: string reads: type: array items: type: object properties: path: type: string value: nullable: true description: >- A JSON value, as the program reads it. Numbers as written. required: - path required: - question - kind - role description: The questions still open. referrals: type: array items: type: object properties: name: type: string description: >- The referral’s name. A referral on the items of a keyed list is one per item, named by the item’s address. state: type: string enum: - Unknown - NotReferred - Open - Approved - Declined role: type: string description: The lowest role that may sign it off. because: type: string lapsed: type: boolean description: >- A sign-off was given and no longer counts: a value it reads changed. reads: type: array items: type: object properties: path: type: string value: nullable: true description: >- A JSON value, as the program reads it. Numbers as written. required: - path required: - name - state - role - because - lapsed - reads invalid: type: array items: type: object properties: code: type: string description: The rule’s code, or the referral’s name. message: type: string path: type: string cite: nullable: true description: A JSON value, as the program reads it. Numbers as written. required: - code - message - path description: Answers the contract refuses. quotes: type: array items: type: object properties: name: type: string outcomes: type: object additionalProperties: nullable: true description: >- Each rating outcome by name, numbers as the program computed them. An outcome on the items of a keyed list is an object by item key. stands: type: boolean description: The present answers are the ones quoted. bound: type: boolean lapsed_by: type: array items: type: string description: What changed since the quote. required: - name - outcomes - stands - bound required: - stage - outcomes - declines - open - referrals - invalid - quotes securitySchemes: bearerAuth: type: http scheme: bearer description: 'Effective API key. Send Authorization: Bearer sk-eai-...' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.