Skip to content

Recommend evaluators intelligently during eval init #323

@placerda

Description

@placerda

agentops eval init currently relies on a static baseline evaluator set unless evaluators are explicitly configured. It should inspect the configured agent and dataset shape, reuse the evaluator recommendation logic from agentops eval run, and pass the recommended built-in evaluators to azd while still respecting explicit evaluator overrides.

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions