docs: add experiments section with programmatic execution guide

[nirga]

Summary

• Add new Experiments section to documentation with comprehensive guide on running experiments from code
• Include setup instructions, task function patterns, and complete customer support example
• Update navigation in mint.json to include new experiments section

Test plan

• Verify new documentation renders correctly in docs site
• Check that navigation includes Experiments section
• Validate code examples are properly formatted

🤖 Generated with Claude Code

---

Important

Adds a new documentation section for programmatically running experiments with the Traceloop SDK and updates navigation.

• Documentation:
  • Adds experiments/running-from-code.mdx with a guide on running experiments programmatically using the Traceloop SDK.
  • Includes setup instructions, task function patterns, and a complete example for customer support.
• Navigation:
  • Updates mint.json to include a new "Experiments" section in the navigation.

^{This description was created by for 32edf73. You can customize this summary. It will automatically update as commits are pushed.}

Summary by CodeRabbit

• Documentation
  • Added a guide for running experiments programmatically with the Traceloop SDK, covering setup, task function patterns, evaluators, execution, and error handling.
  • Included templates and an end-to-end example comparing multiple approaches (e.g., different tones) with result summaries.
  • Provided parameter reference and best practices for experiment slugs, dataset versioning, and evaluator selection.
• Chores
  • Updated site navigation with a new “Experiments” section featuring the “Running from Code” page.

[coderabbitai]

Caution

Review failed

The pull request is closed.

Walkthrough

Adds a new documentation page explaining how to run experiments programmatically via the Traceloop SDK and updates site navigation to include an “Experiments” group linking to this page. No code logic or public APIs were modified.

Changes

Cohort / File(s)	Summary
Docs: Programmatic Experiments experiments/running-from-code.mdx	New doc detailing Traceloop experiment setup, async task patterns, evaluator usage, running experiments, comparing approaches, and best practices, with full code examples.
Site Navigation Update mint.json	Adds an "Experiments" group with page experiments/running-from-code to the navigation between "Quick Start" and "Monitoring".

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Poem

I hopped through docs with carrot-bright delight,
New trails for experiments now in sight.
Slugs and tasks in tidy rows,
Async dreams where output flows.
In nav I nest, a page brand-new—
Let’s run, compare, and test what’s true! 🥕✨

Tip

🔌 Remote MCP (Model Context Protocol) integration is now available!

Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats.

---

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

💡 Knowledge Base configuration:

• MCP integration is disabled by default for public repositories
• Jira integration is disabled by default for public repositories
• Linear integration is disabled by default for public repositories

You can enable these sources in your CodeRabbit configuration.

📥 Commits

Reviewing files that changed from the base of the PR and between edd6ef7 and 32edf73.

📒 Files selected for processing (2)

• experiments/running-from-code.mdx (1 hunks)
• mint.json (1 hunks)

✨ Finishing Touches

🧪 Generate unit tests

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch experiements-docs

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR/Issue comments)

Type @coderabbitai help to get the list of available commands.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Status, Documentation and Community

• Visit our Status Page to check the current availability of CodeRabbit.
• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[ellipsis-dev]

Important

Looks good to me! 👍

Reviewed everything up to 32edf73 in 39 seconds. Click for details.

• Reviewed 257 lines of code in 2 files
• Skipped 0 files when reviewing.
• Skipped posting 3 draft comments. View those below.
• Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.

1. experiments/running-from-code.mdx:37

• Draft comment:
  Consider adding 'import openai' for completeness in this snippet.
• Reason this comment was not posted:
  Confidence changes required: 50% <= threshold 50% None

2. experiments/running-from-code.mdx:235

• Draft comment:
  Append a newline at end of file for POSIX compliance.
• Reason this comment was not posted:
  Confidence changes required: 33% <= threshold 50% None

3. mint.json:147

• Draft comment:
  New 'Experiments' group added; ensure the referenced page exists.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 50% The comment is asking the PR author to ensure that a referenced page exists, which falls under the category of asking the author to double-check something. This violates the rule against asking the author to confirm or ensure something.

Workflow ID: wflow_g99hyOrXlZbvhlDf

^{You can customize by changing your verbosity settings, reacting with 👍 or 👎, replying to comments, or adding code review rules.}