Overview

Entities are the configurable resources that make up an AI GO! evaluation. Each entity is defined declaratively in a YAML file (or constructed via the SDK) and referenced by the CLI. Together they describe what you evaluate (AI apps, datasets, models), how you evaluate it (tasks, evaluations, runs), and what comes out (task result logs, traces).

Available Entities

Entity	Description
Policies	Quality gates for an AI app that check whether evaluation results meet defined thresholds.
AI Apps	A workspace for executing technical evaluations for a given AI use case.
Datasets	A collection of data used as a source of samples for model evaluation.
Dataset Generators	A modular, declarative way to create synthetic datasets.
Evaluations	A set of configured tasks run against a model or a dataset.
Models	An inference endpoint served by an external provider or your own infrastructure.
Model Adapters	Converts models with different input/output formats into a common schema.
Run	A unified entry point that defines what evaluation to run and all of its dependencies.
Tasks	Defines the execution flow of an evaluation of a model or a dataset.
Task Result Logs	Captures the full output of a task execution: metrics, per-sample evidence, traces, and errors.
Trace	A conversation between a user and an agent: a sequence of messages, function calls, and function call outputs.
Config Specification	Defines the allowed configuration options for a task or a dataset generator.