> For the complete documentation index, see [llms.txt](https://docs.turboload.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.turboload.ai/ai-intelligence-suite/performance-advisor-chat.md). # AI Performance Advisor & Chat > **On-Demand Speed Intelligence:** Query your store's live performance data in plain English to receive instant root-cause diagnoses, copyable Liquid code fixes, and shareable technical handoffs. Understanding why your store's speed changes can be daunting. The **AI Performance Advisor** acts as your dedicated on-demand performance engineer, translating complex browser waterfall data and Core Web Vitals into plain-English answers and actionable solutions. ![TurboLoad AI Performance Advisor showing interactive conversational diagnosis, script latency breakdown, and Markdown/JSON exports](https://3104101331-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F4kkyKWXlRlIIrT0xXLUz%2Fuploads%2Fgit-blob-b9213495d34456a8843a2962deb969b85f66c0ec%2F05_ai_chat.png?alt=media) *** ## Direct Answer: How does the TurboLoad AI Performance Advisor work? The TurboLoad AI Performance Advisor analyzes your store's real-user speed metrics, theme structure, and third-party script execution in real time. Merchants can ask natural language questions (e.g. *"Why did my mobile speed drop?"* or *"Which app is slowing down checkout?"*) to receive immediate root-cause breakdowns, estimated metric lift projections, and copyable Liquid code fixes verified for Shopify themes. *** ## What Can the AI Advisor Do? The AI Advisor connects directly to your store's live telemetry, web vitals metrics, and theme structure to answer questions like: * *"Why did my mobile performance score drop from 88 to 72 over the weekend?"* * *"Which installed apps are creating the biggest lag during mobile checkout?"* * *"What specific code changes should I make in `theme.liquid` to improve Largest Contentful Paint?"* * *"Can you write a Liquid snippet to preload my hero banner image on the homepage?"* *** ## Step-by-Step: Using the AI Chat ### 1. Open the Chat Interface Click **AI Chat** (`/app/chat`) in the TurboLoad navigation bar. ### 2. Ask a Question or Choose a Quick Prompt You can type any question or click one of the pre-built quick prompt pills: * ⚡ **Diagnose My Largest Issues** * 📱 **Improve Mobile INP Score** * 🛒 **Analyze App Script Overhead** * 🖼️ **Optimize Image & Media Assets** ### 3. Review Actionable Root-Cause Guidance The advisor responds with: * **Root-Cause Analysis:** The exact script, image, or theme section triggering the latency. * **Estimated Metric Impact:** How much LCP or INP improvement to expect. * **Code Snippets:** Drop-in Liquid or HTML adjustments with clear instructions. *** ## Exporting Conversations (Markdown & JSON) Need to hand off the AI's recommendations to your web agency, freelance developer, or internal team? You can export any conversation with a single click: 1. In the top right corner of the chat window, click **Export**. 2. Select your preferred format: * **Download as Markdown (`.md`):** Perfect for pasting into GitHub Issues, Notion docs, Jira tickets, or Linear tasks. File name format: `turboload-chat-.md`. * **Download as JSON (`.json`):** Formatted structured portable bundle (`turboload.chat.export`) suitable for external AI models, audits, or backup records. File name format: `turboload-chat-.json`. *** ## Privacy & Enterprise Data Governance TurboLoad is engineered with strict data privacy boundaries: * **Zero Customer Data Exposure:** Shopper personal information (PII), customer names, email addresses, order amounts, and payment tokens are never accessed or sent to AI models. * **Isolated Store Scoping:** Diagnoses are generated strictly within your store's verified boundary without cross-tenant data leakage. * **Enterprise Security:** All queries and AI responses are encrypted in transit via TLS 1.3. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## 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, and the optional `goal` query parameter: ``` GET https://docs.turboload.ai/ai-intelligence-suite/performance-advisor-chat.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.