Gen AI Evaluation Toolkit on AWS

v2.0.0

Copyright © 2026 Amazon Web Services, Inc. and/or its affiliates. All rights reserved. Amazon’s trademarks and trade dress may not be used in connection with any product or service that is not Amazon’s, in any manner that is likely to cause confusion among customers, or in any manner that disparages or discredits Amazon. All other trademarks not owned by Amazon are the property of their respective owners, who may or may not be affiliated with, connected to, or sponsored by Amazon.

Interface: CreateJobSchedulerInput¶

Request parameters for creating or updating a job scheduler. Fields required depend on jobType: FULL requires testCases + scorers, SCORE requires scorers + (sourceReportId or testResults), APP_INVOKE requires testCases.

Extended by¶

CreateJobSchedulerCommandInput

Properties¶

app?¶

optional app?: AppConfig

App invocation configuration (optional, for FULL and APP_INVOKE)

cron¶

cron: string

Cron expression defining when jobs should run (e.g., '0 0 * * *' for daily)

evaluatorName¶

evaluatorName: string

Name of the evaluator to run

experimentName?¶

optional experimentName?: string

Experiment name for grouping scheduled runs

jobType¶

jobType: JobType

Type of job to submit on each schedule trigger

scorers?¶

optional scorers?: Record\<string, ScorerConfig | null>

Scorer configurations keyed by scorer name (required for FULL and SCORE)

sourceReportId?¶

optional sourceReportId?: string

Source report ID to re-score (for SCORE jobs, mutually exclusive with testResults)

testCases?¶

optional testCases?: TestDataSource

Source of test cases (required for FULL and APP_INVOKE)

testResults?¶

optional testResults?: InlineTestResult[]

Inline test results for scoring (for SCORE jobs, mutually exclusive with sourceReportId)

Table of contents