Rewrite What Is Scorecard page for simulation platform positioning

[Rutledge]

Summary

• Full rewrite of intro/what-is-scorecard.mdx to align with the new "simulation platform for agent self-improvement" positioning, replacing the old "AI evaluation platform" identity
• Introduces new problem framing ("the bottleneck is feedback, not building"), a 4-step simulation workflow (encode → simulate → compare → ship), use-case cards, integration section (Claude Agent SDK, LangChain, Any LLM), and "Built by simulation engineers" heritage section
• Updates intro/overview.mdx description, opening paragraph, card copy, and footer to match the new messaging

Test plan

• Run npx mintlify dev and verify both pages render correctly
• Confirm GIF still loads on the What Is Scorecard page
• Verify <Steps>, <CardGroup>, <Card>, <Tip>, and <Frame> components render properly
• Check all internal links resolve (ran npx mintlify broken-links — no new broken links introduced)

[gemini-code-assist]

Summary of Changes

Hello @Rutledge, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request rebrands Scorecard's core messaging across key introductory documentation pages. The primary goal is to shift the product's identity from an "AI evaluation platform" to a "simulation platform for AI agent self-improvement," emphasizing its role in accelerating agent development through large-scale simulation and automated feedback. These changes aim to provide a clearer, more impactful narrative for users engaging with the platform's capabilities.

Highlights

• Content Repositioning: The documentation has been significantly updated to reflect Scorecard's new positioning as a "simulation platform for AI agent self-improvement," moving away from the previous "AI evaluation platform" identity.
• what-is-scorecard.mdx Rewrite: The intro/what-is-scorecard.mdx page has been fully rewritten to introduce a new problem framing, a 4-step simulation workflow, use-case cards, integration details, and a heritage section.
• overview.mdx Updates: The intro/overview.mdx page has been updated with new descriptions, introductory text, card copy, and footer messaging to align with the new product positioning.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• intro/overview.mdx
  • Updated the page description to "The simulation platform for building frontier AI agents".
  • Revised the introductory paragraph to emphasize Scorecard as a "simulation platform for AI agent self-improvement".
  • Modified the "What is Scorecard?" card text to "Learn how simulation drives agent self-improvement".
  • Changed the support email text from "AI evaluation setup" to "AI agent setup".
• intro/what-is-scorecard.mdx
  • Updated the page description to highlight simulation for building frontier AI agents.
  • Rewrote the main introductory paragraph to define Scorecard as a simulation platform for AI agent self-improvement.
  • Replaced the "Why you need AI evals" section with a new section titled "The bottleneck is feedback, not building," which includes a comparison tip.
  • Introduced a detailed "How Scorecard works" section using a component, outlining a 4-step simulation workflow (Encode, Simulate, Compare, Ship).
  • Replaced previous sections on "Who uses Scorecard" and "What Scorecard provides" with a new "What you can do" section, featuring a of six use-case cards.
  • Added a new "Works with your agent stack" section, detailing integrations with Claude Agent SDK, LangChain, and Any LLM using a .
  • Included a "Built by simulation engineers" section, highlighting the team's background.
  • Replaced the "Next steps" section with a new "Get started" section, offering options to run an evaluation, try the Playground, or book a demo.
  • Maintained the support email contact information.

Activity

• No human activity (comments, reviews, etc.) has been recorded on this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[github-actions]

🖼️ Image Usage Check ✅

All 236 images in the repository are being used! No unused images found.

Great job keeping the repository clean! 🎉

[gemini-code-assist]

Code Review

This pull request is a comprehensive rewrite of the 'What Is Scorecard?' page to align with the new 'simulation platform' positioning, along with corresponding updates to the 'Overview' page. The changes are well-executed and effectively communicate the new messaging. I've provided a couple of minor suggestions to improve clarity and consistency in the documentation.