# Mobb Tracy ## Overview Mobb Tracy is an AI code intelligence platform that provides line-level visibility into AI-generated code in your pull requests. It shows exactly which lines were generated by AI, which model was used, and what prompt created them - not to blame, but to learn and improve code review processes. As AI writes more code, traditional code review has become harder and less clear. Tracy solves this by giving reviewers the context they need to focus on the right areas and understand how AI was used in the development process. ## What Tracy Shows You * **AI-generated code identification**: See exactly which lines were written by AI vs manually * **Model information**: Know which AI model was used for each code segment * **Prompt visibility**: View the actual prompts that generated the code * **Code review focus**: Quickly identify AI-generated changes that need careful review ## Use Cases Tracy serves three main customer segments with distinct value propositions: ### 1. Security Teams For security professionals who need visibility into AI's impact on code security: * **Full transparency** of where AI code exists across teams and projects * **Security correlation** - identify which AI tools, models, and prompts created security vulnerabilities * **Risk assessment** - understand which teams need security focus based on AI usage patterns * **Compliance support** - maintain audit trails for AI-generated code in regulated environments ### 2. AI Adoption (Enterprise) For medium to large companies still building AI development practices: * **Adoption metrics** - track and measure AI coding adoption across the organization * **Responsible rollout** - enable AI development in a controlled, transparent manner * **Developer confidence** - reduce resistance to AI tools through transparency and accountability * **Process improvement** - help teams transition from manual to AI-assisted development safely ### 3. Continuous Improvement (Advanced Teams) For organizations with mature AI adoption looking to optimize their practices: * **Knowledge sharing** - learn from top-performing AI developers across the team * **Prompt optimization** - identify and share effective prompts and AI interaction patterns * **Efficiency analysis** - understand what makes a productive vs. wasteful AI coding session * **Best practice development** - establish data-driven guidelines for effective AI usage ## Supported IDEs Tracy currently supports: * **Cursor IDE** - [Setup Guide](/mobb-user-docs/getting-started/mobb-tracy/cursor.md) * **VS Code** with **GitHub Copilot** - [Setup Guide](/mobb-user-docs/getting-started/mobb-tracy/vs-code-+-github-copilot.md) * **Claude Code** - [Setup Guide](/mobb-user-docs/getting-started/mobb-tracy/claude-code.md) More IDE integrations coming soon. ## Seeing Tracy in Action Once installed, Tracy automatically analyzes your pull requests and provides: ### Pull Request Annotations Every PR shows a detailed analysis including: * Total lines added * AI-generated lines count * AI percentage of the changes * Line-by-line AI attribution
### Detailed Code View Click "View results in Tracy" to see: * Which specific lines were AI-generated * The AI model used (GPT-4, Claude, etc.) * The original prompt that generated the code * Context about the generation process
## Tracy Time Machine Tracy Time Machine is a feature of the Mobb Tracy extension (applicable for VS Code and Cursor) that allows you to travel back and review the AI conversation history for specific lines of code. To use Tracy Time Machine: 1. Select a particular line in the code. 2. Click on the Tracy icon on the bottom right of the IDE where it says "Tracy" with a robot icon.
Tracy Icon
3. Tracy will act as a "time machine," going back in time to show you all the conversation you had with the AI coding agent that led to the current code. This includes your prompt, the AI's responses, and your subsequent prompts.
Tracy Time Machine History
4. From there, you can click on "Continue Conversation," which will bring the history and the context of the previous conversation into the current chatbox with the AI to further the conversation.
Continue Conversation
## Getting Started **Choose your IDE setup**: * [Cursor IDE guide](/mobb-user-docs/getting-started/mobb-tracy/cursor.md) if you're using Cursor * [VS Code with GitHub Copilot guide](/mobb-user-docs/getting-started/mobb-tracy/vs-code-+-github-copilot.md) if you're using VS Code with GitHub Copilot * [Claude Code guide](/mobb-user-docs/getting-started/mobb-tracy/claude-code.md) if you're using Claude Code --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.mobb.ai/mobb-user-docs/getting-started/mobb-tracy.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.