MUST use when creating flows.
MUST use when creating raw apps.
MUST use when creating or modifying a data pipeline, a set of scripts marked `pipeline` and wired together by `on` / `materialize` annotations.
Author and run black-box benchmark cases for the Windmill AI generation modes (flow/app/script/cli/global) in ai_evals/. Use when adding or changing eval cases, or when running before/after benchmarks for AI chat / copilot changes.
MUST use when using the CLI, including debugging job failures and inspecting run history via `wmill job`.
MUST use when reading or changing workspace settings, or the settings.yaml file `wmill sync` keeps.
MUST use when creating or changing an AI agent, the reusable `ai_agent` resource the Agents page lists.
MUST use when managing resources.