rewrite README, better demo GIF

[ofershap]

Summary

• Full README rewrite addressing all feedback
• New demo GIF with 5 tool calls (checkout form scenario)
• Story section, accordion FAQ, collapsed architecture
• Comparison table without negative language
• Teach-your-agent section moved up

Test plan

• Preview README on GitHub

Made with Cursor

[gemini-code-assist]

Summary of Changes

Hello, 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 significantly overhauls the project's documentation by completely rewriting the README.md file. The changes aim to enhance user understanding, provide clearer examples of the tool's functionality, and improve the overall structure and presentation of information for both new and existing users.

Highlights

• README Rewrite: The entire README.md file has been rewritten to improve clarity, conciseness, and overall presentation, addressing previous feedback.
• New Demo GIF: A new demo GIF has been added, showcasing a checkout form scenario with 5 tool calls, providing a more illustrative example of the agent's capabilities.
• Content Restructuring: New sections like 'Your Agent Works in a Void' were introduced, while 'Architecture', 'Development', and 'FAQ' sections were collapsed into accordions for better readability. The 'Teach Your Agent' section was also moved to a more prominent position.
• Comparison Table Refinement: The comparison table with other tools ('How Others Compare') was updated to remove negative language and provide a more neutral, concise comparison.
• Tool Descriptions Update: The 'Tools' section was renamed to 'What It Can Do' and its descriptions were simplified and categorized for easier understanding.

🧠 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

• README.md
  • Removed the initial tagline and repositioned a bolded version for greater emphasis.
  • Updated badge labels for the Chrome Extension and Cursor for conciseness.
  • Replaced the previous agent interaction example with a new, more detailed checkout form validation scenario.
  • Introduced a new 'Your Agent Works in a Void' section to articulate the problem statement more effectively.
  • Restructured the 'Quick Start' section, converting numbered steps to bullet points and simplifying the accompanying text.
  • Consolidated manual installation instructions for other MCP clients and the Chrome extension source loading into collapsible details sections.
  • Removed the dedicated 'Step 3 (optional): Install Cursor shortcuts' section, integrating its content into a new 'Teach Your Agent' section.
  • Renamed 'Why Not Playwright MCP / Chrome DevTools MCP?' to 'How Others Compare' and refined the comparison table for clarity.
  • Removed the 'Usage Examples' section entirely.
  • Introduced a new 'Teach Your Agent' section, incorporating setup commands for Cursor and Claude Code.
  • Renamed 'Tools' to 'What It Can Do' and reorganized tool descriptions into categories (See, Interact, Navigate, Debug) with simplified explanations.
  • Removed the detailed 'How It Works' and 'Agent Config' sections, collapsing the architecture diagram under a
    Details

    tag.
  • Added details about connection reliability (exponential backoff, health checks, timeouts) to the 'Configuration' section.
  • Converted 'Architecture', 'Development', and 'FAQ' sections into collapsible
    Details

    elements.
  • Simplified answers within the FAQ section for brevity.
  • Updated the copyright symbol from '©' to '©'.

Activity

• No specific activity or comments were recorded for this pull request.

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. ↩

[gemini-code-assist]

Code Review

This pull request provides a comprehensive rewrite of the README.md file. The new version is much clearer, better structured, and more engaging for new users. The use of collapsible sections for detailed information is a great choice to keep the main flow clean. I've made one suggestion to improve the clarity of the comparison table, where some of the concise phrasing could be slightly ambiguous. Overall, this is an excellent update.

_{Note: Security Review has been skipped due to the limited scope of the PR.}

[gemini-code-assist]

While the rest of the README has been made more concise without losing clarity, some cells in this comparison table have become a bit ambiguous. For example, 'No, launches new' is less clear than 'No, launches new browser'. Similarly, for the 'Setup' row, describing the action (e.g., 'Launch headless browser') is clearer than just naming the component ('Headless browser'). I suggest restoring a bit more detail here for clarity.

Suggested change

	| Uses your existing browser | Yes | No, launches new | Partial, needs debug port |
	| Sessions and cookies | Already there | Fresh profile | Manual setup |
	| Works behind corporate SSO | Yes | No | Depends |
	| Setup | Install extension, add MCP config | Launch headless browser | Launch Chrome with `--remote-debugging-port` |
	| Feels like | Giving the agent your screen | Giving the agent a lab browser | Giving the agent a debug session |
	The core difference: Playwright and Chrome DevTools MCP create or attach to a separate browser. Real Browser MCP controls the one you're already using. If your app needs auth, complex state, or specific cookies, you don't have to recreate any of that.
	| Setup | Extension + MCP config | Headless browser | Chrome with `--remote-debugging-port` |
	| Uses your existing browser | Yes | No, launches new browser | Partial, needs debug port |
	| Sessions and cookies | Already there | Fresh profile | Manual setup |
	| Works behind corporate SSO | Yes | No | Depends |
	| Setup | Extension + MCP config | Launch headless browser | Launch Chrome with `--remote-debugging-port` |