Add experimental AI Evaluations topic page#13471
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a new documentation page on 'AI Evaluations' (experimental) for Dart and Flutter, detailing their evaluation frameworks and testing methodologies, and updates the sidebar navigation to include this new page. A review comment suggests a grammatical improvement to ensure proper parallel structure in a list of actions.
| To explore the evaluation strategy, | ||
| view the open-source dataset, scoring rubrics, | ||
| or get involved with community benchmark datasets, | ||
| visit the [Flutter Evals repository](https://github.com/flutter/evals). |
There was a problem hiding this comment.
The list of actions starting with 'To' has a grammatical parallelism issue. 'view the open-source dataset, scoring rubrics' lacks a conjunction. Adding 'and' clarifies that 'view' applies to both nouns and maintains a proper parallel structure.
| To explore the evaluation strategy, | |
| view the open-source dataset, scoring rubrics, | |
| or get involved with community benchmark datasets, | |
| visit the [Flutter Evals repository](https://github.com/flutter/evals). | |
| To explore the evaluation strategy, | |
| view the open-source dataset and scoring rubrics, | |
| or get involved with community benchmark datasets, | |
| visit the [Flutter Evals repository](https://github.com/flutter/evals). |
|
Staged preview of the updated docs.flutter.dev site (updated for commit c6abae6): https://flutter-docs-prod--docs-pr13471-ai-evals-docs-682e8amb.web.app |
2 participants
Introduce a new, high-level AI Evaluations page containing an overview of evaluation strategy, CUJs, and dimensions.
Changes:
/ai/evalshighlighting the experimental nature of evaluations and linking directly to the main repository (https://github.com/flutter/evals).ai.ymlsidebar under Developer experience.