> 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/readme.md).

# What Kula Intelligence is

**Kula Intelligence is AI that actually knows your studio.**

You already use an AI assistant — Claude, maybe ChatGPT. It gives great general advice and useless specific answers, because it can't see *your* numbers. Kula Intelligence fixes that. It gives your AI assistant a safe, private window into your studio's own data, so when you ask **"who haven't I seen on the mat lately?"** you get an answer built from your members, your attendance, your sales — not generic fitness-industry advice.

You ask questions in plain English, in the assistant you already pay for. No new dashboard to learn. No spreadsheets.

![The Kula Intelligence console — where you connect data, manage AI access, and see your studio's status](/files/hKGu6crdfFvV1J3Xvo6I)

## One shared brain for your whole studio

Kula Intelligence isn't a private window for one person — it's the **shared brain for the whole business**, and it's **always up to date**. It reads straight from the tools you already run on — your booking platform, your payments, your accounting — and keeps itself current, so there's no spreadsheet to refresh and no export to remember. Whenever you ask, you're asking the live state of the studio.

* **A whole-of-business view.** Everything you connect sits in one place, so a single question can cross bookings, sales, and accounting at once — instead of three dashboards that don't talk to each other.
* **Your team, each seeing only what they should.** Give a coach, a manager, or a bookkeeper their own access, set to the right level — some see trends only, some see member names, some see contact details. The assistant can never reveal more than that person's level allows, so the whole team can share one brain without sharing everything. See [Permission levels](/connect-claude-and-access/scopes.md).
* **Everyone on the same page.** The playbooks you build are **shared skills**: publish one and everyone connected to the studio runs the exact same analysis the same way — so your team is always looking at the same thing, not ten slightly different versions of it. See [What skills are](/skills/skills.md).

And soon you'll be able to **save an answer and share it** with others on your team, so a useful result doesn't stay locked in one person's chat.

## Who it's for

Owners and operators of boutique fitness studios — reformer pilates, yoga, strength and group training, climbing, boutique cycle. The people who spend Sunday evenings staring at three dashboards trying to work out whether next month is going to be okay.

You do **not** need to be technical. If you can install an app and copy and paste, you can set this up yourself in about ten minutes. A consultant can do it *with* you or *for* you if you'd rather — but nothing here requires one.

## What you can ask

Once your data is connected, you ask things like:

* *"Who'd love a check-in from me this week?"*
* *"How is the reformer cohort tracking — are they staying with us?"*
* *"Which classes are quietly growing, and which could use a refresh?"*
* *"Draft a warm note to the members I haven't seen since May."*
* *"Are we going to be okay next month?"*

See [What you can ask](/get-started/ask.md) for the full library, grouped by the problem you're trying to solve.

## How it works

1. **Create your account and connect your data.** Plug in the tools you already use — your booking platform, your payments, your accounting. It's a guided setup; you paste a key or click through a sign-in, and we pull your history in. See [Set up & get your first answer](/get-started/start.md).
2. **Connect your AI assistant.** One link, one sign-in. See [Connect Claude](/connect-claude-and-access/claude.md).
3. **Ask questions.** In Claude or ChatGPT, just like you talk to it now — except now it can see your studio.
4. **Stay in control.** You can see exactly what's been read and when, and you can disconnect any time with one click. See [Is my data safe?](/get-started/trust.md).

## What makes it trustworthy

* **Your data is yours alone.** Every studio gets its own private database. There is no path for one studio's question to be answered with another studio's data — they aren't even stored together. Read [Security & data handling](/trust-and-legal/security.md).
* **It reads, it doesn't spend.** Kula Intelligence can draft a win-back email; it never sends money, never charges a card, never posts on your behalf.
* **You decide how much it can see.** Permission levels let you keep member names and contact details hidden when you only need the big picture. See [Permission levels](/connect-claude-and-access/scopes.md).

## What it isn't

* **Not a new CRM.** It doesn't replace your booking platform or payment processor. It reads from them.
* **Not another dashboard.** The interface is the AI assistant you already use. We show no charts.
* **Not a marketing autopilot.** It can write the email; you send it.

## Where to go next

* **Setting it up yourself?** → [Set up & get your first answer](/get-started/start.md)
* **A consultant helping a studio?** → [Helping a studio go faster](/for-consultants/consultants.md)
* **A developer integrating it?** → [Developer overview](/for-developers/overview.md)

***

*Kula Holdings Pty Ltd · Sydney*


---

# 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.kula.digital/readme.md?ask=<question>&goal=<endgoal>
```

`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.