docs(evaluator): mark agent-eval platform-plugin support as in progress

[SandyChapman]

What

Marks agent-eval platform-plugin execution as in progress, so the docs don't imply a capability that isn't shipped.

• Adds a <Note> on the Agent Evaluation landing page: the section runs through the local SDK (AgentEvaluator().run()); running agent evals through the NeMo Platform plugin as durable platform jobs — the way dataset-driven evaluation already can — is under active development.
• Softens the "Runs locally" key-property bullet, which asserted "the same run can also be submitted as a platform job" — a forward reference to a path the plugin doesn't expose for agent evals yet.

Why

Follow-up to the agent-eval docs (#710). Reviewer feedback flagged that the pages are SDK-only while forward-referencing a submit/job path that doesn't exist for agent evals. This keeps the docs honest until plugin support lands.

Notes

• Docs-only; one file (docs/evaluator/agent-eval/index.mdx).
• Release-notes coverage for agent evaluation is deferred to the 0.3 release notes, to be added when that page is started.

🤖 Generated with Claude Code

Summary by CodeRabbit

• Documentation
  • Clarified that platform-plugin support for agent evaluations is still in progress.
  • Updated examples to use the local SDK for running evaluations.
  • Revised key-property guidance to note that evaluations run locally without requiring platform services.

[github-actions]

🌿 Preview your docs: https://nvidia-preview-agent-eval-plugin-docs-schapman.docs.buildwithfern.com/nemo-platform

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: f8449511-1838-46d4-8543-92c34bf1d463

📥 Commits

Reviewing files that changed from the base of the PR and between 1a0589b and deb38b8.

📒 Files selected for processing (1)

• docs/evaluator/agent-eval/index.mdx

---

📝 Walkthrough

Walkthrough

The agent-eval documentation clarifies that platform-plugin support is in progress and directs readers to use AgentEvaluator().run() locally.

Changes

Agent evaluation documentation

Layer / File(s)	Summary
Execution guidance docs/evaluator/agent-eval/index.mdx	Adds an introductory note directing readers to the local SDK and updates the “Runs locally” property to reflect platform-plugin support status.

Possibly related PRs

• NVIDIA-NeMo/nemo-platform#710: Updates the same agent-eval page with related local and platform-plugin guidance.

Suggested labels: docs

Suggested reviewers: arpitsardhana, ngoncharenko

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately summarizes the doc update marking agent-eval platform-plugin support as in progress.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch agent-eval-plugin-docs/schapman

---

_{Comment @coderabbitai help to get the list of available commands.}

[github-actions]

Suite	Lines Covered	Line Rate	Branch Rate
Unit Tests	25521/32723	78.0%	62.6%
Integration Tests	14723/31372	46.9%	19.3%