Infrastructure · Data artifact
Evaluation Workflow Definition
Data artifactInfrastructureInfrastructurearc:EvaluationWorkflowDefinition
A declarative CI workflow file specifying the triggering events and path filters, environment, and steps for running evaluation, reporting and gating.
Responsibility. Declares when and how continuous evaluation runs.
Also known as: Agent CI/CD pipeline definition (workflow YAML)
Relationships
configures structural
Design guidance
- SHOULD use path filters so only changes to agent code, tools, prompts and evaluation infrastructure trigger evaluation.
- SHOULD centralise shared settings (runtime version, registry, tracking URI) as workflow-level variables rather than repeating them per job.
Sources
- Ch3.1B: T. Nguyen, "Implement Evaluation Pipelines and Task Benchmarks - Guided Practice," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.1B. ISBN: 9798244538229.
- Ch4.2: T. Nguyen, "Deployment and Scaling," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.2. ISBN: 9798244538229.