> For the complete documentation index, see [llms.txt](https://docs.kula.digital/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.kula.digital/get-started/first-diagnostic.md). # Run your first diagnostic Once your data is connected, the single most useful thing you can do is run a **diagnostic** — a structured work-up of your studio that the AI does *in order*, showing you what it finds at each step before moving on. We call it **Studio Ignition**. You don't have to learn it. You just ask Claude to run it, answer a few questions about your studio when it asks, and read what comes back. ## Why a diagnostic, not just a question Most studios think they have a data problem. They actually have a **linkage** problem. Your booking platform holds your attendances, your plans, and your sales side by side — but it doesn't really connect them. So when you ask *"how is the reformer cohort tracking?"*, the honest answer is usually *nobody knows*, because the attendances aren't tied to the plans, and the plans aren't tied to the sales. The diagnostic fixes that first. It stitches your data together and checks its own work, so every answer after it stands on solid ground. ## How to run it In Claude, ask: > *"Run the Studio Ignition diagnostic on my studio."* The AI will walk through it with you. Early on it asks you to confirm a few things about how your studio works — that's the **operator intake**, and it's worth doing carefully because everything downstream leans on it. Set aside an unhurried hour for the full run. You can also stop after the first part and come back later — it remembers where it got to. ## What it does, in two parts **Part one — what's actually true.** The diagnostic establishes the honest picture first, with no rosy projections: * Loads your studio's data and the quirks of your booking platform. * Counts your activity month by month, and flags gaps — a month with zero attendances at a studio that was open is a data gap, not a quiet month. * Connects each attendance to the plan it was drawn against and the sale that paid for it, then tells you how much of your data it could link. * Runs data-quality checks and reports each as pass, warn, or fail. You sniff-test this picture and confirm it before anything else happens. **No projected upside or recoverable revenue is shown in part one — ever.** That's deliberate: you should trust the foundation before you act on it. **Part two — what to do about it.** Only once you've confirmed the picture does the diagnostic move on to opportunities: where revenue is slipping, which relationships hold your members, how your classes and pricing are really performing, and where your marketing spend goes. Each suggestion is traced back to your own numbers, and the theme throughout is *more human, not less.* ## What you end up with A clear, honest view of your studio's reality — not a dashboard, but a foundation. After it, questions like *"who haven't I seen in a while?"*, *"how do memberships compare to class packs for us?"*, or *"is the new instructor's class finding its people?"* all have a solid answer. The diagnostic saves what it builds, so future questions are fast and consistent. ## What's next * [What you can ask](/get-started/ask.md) — keep going with everyday questions. * [Your weekly rhythm](/get-started/your-rhythm.md) — fold this into a weekly habit. * Curious how the diagnostic is built, or want to tailor it? See [Skills](/skills/skills.md). --- # 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: ``` GET https://docs.kula.digital/get-started/first-diagnostic.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.