Add agentic AI scorers to supported models and frameworks reference

[nrichers]

Pull Request Description

What and why?

Adds documentation for agentic AI evaluation using DeepEval integration to the supported models and frameworks page.

Context: While reviewing a product brief from Marketing, I noticed that we were referring to recently added agentic AI tests which I had not seen before. Had a convo with the codebase to get the details.

Changes:

• Add "Agentic AI" tab to the model type quick reference with link to detailed evaluation docs
• Add "Agentic AI evaluation" section with:
  • Available tests: TaskCompletion, PlanQuality, PlanAdherence, ToolCorrectness, ArgumentCorrectness
  • Test requirements table showing model requirements and input columns for each test

sc-15351

How to test

Try the live preview: Supported models and frameworks

Output

What needs special review?

N/A

Dependencies, breaking changes, and deployment notes

None — documentation only.

Release notes

N/A

Checklist

• What and why
• How to test
• Labels applied
• PR linked to Shortcut
• Documentation updated

[github-actions]

Lighthouse check results

⚠️ WARN: Average accessibility score is 0.87 (required: >0.9) — Check the workflow run

Show Lighthouse scores

Folder depth level checked: 0

Commit SHA: 8792c8b

Modify the workflow to check a different depth:

• 0: Top-level navigation only — /index.html, /guide/guides.html, ...
• 1: All first-level subdirectories — /guide/.html, /developer/.html, ...
• 2: All second-level subdirectories — /guide/attestation/*.html, ...

Page	Accessibility	Performance	Best Practices	SEO
/developer/validmind-library.html	0.85	0.67	1.00	0.82
/get-started/get-started.html	0.85	0.73	1.00	0.73
/guide/guides.html	0.81	0.70	1.00	0.82
/index.html	0.93	0.67	1.00	0.82
/releases/all-releases.html	0.86	0.69	1.00	0.73
/support/support.html	0.91	0.70	1.00	0.82
/training/training.html	0.85	0.69	0.96	0.73

[github-actions]

PR Summary

This PR makes two primary updates to the documentation:

1. In the file site/developer/model-documentation/install-and-initialize-validmind-for-r.qmd, the paths for the quickstart examples for both model documentation and model validation have been updated. The URLs previously pointed directly to specific R Markdown files in the GitHub repository using the /blob/ path; they are now updated to point to the general quickstart directory using the /tree/ path. This change centralizes the quickstart content and might help users navigate related resources more easily.

2. In the file site/developer/supported-models-and-frameworks.qmd, a new section titled "Agentic AI" has been added. This section introduces agentic AI concepts and details the evaluation integration with DeepEval, including a list of available agentic scorers with their functional descriptions and requirements. This enhances the documentation by informing developers about the capabilities for agentic AI evaluation and the associated metrics.

Overall, these changes improve the accessibility of rapid start examples and extend the documentation to cover agentic AI evaluation workflows.

Test Suggestions

• Verify that the updated quickstart paths correctly resolve to the intended directory in the GitHub repository.
• Ensure that the new Agentic AI section displays correctly in the documentation site and that its formatting is consistent with the rest of the documentation.
• Check that the links to DeepEval and any referenced tools or parameters are accurate and up-to-date.
• Perform a manual review of the rendered documentation to confirm that the new tables and bullet lists are properly formatted.

[nrichers]

Thank you for the review feedback, Anil! I believe I have addressed the review feedback, could you take another look and approve?

For my own reference, here's what I found in the code:

[github-actions]

Validate docs site

✓ INFO: A live preview of the docs site is available — Open the preview

[AnilSorathiya]

Thanks @nrichers ! 👍