# Use Pilotie with your AI

> Connect Claude, ChatGPT, Grok or any MCP assistant to Pilotie next to the built-in helper: it works in your apps and waits for your OK before anything risky goes out.

Source: https://pilotie.geenius.io/docs/use-with-your-ai/

Pilotie has a helper built in, so you do not need this page to use it. It is for the AI you may already have: Claude, ChatGPT, Grok or any assistant that supports MCP can connect to the same workspace once and then work in your apps next to the helper: projects and tasks, documents and tables, invoices and quotes, calendar and bookings, contacts, forms, files, websites and more.

> [!HONEST]
> An outside AI can do a lot, and you stay in charge. Emails to customers and other risky steps wait in Approvals until you say OK, each agent has only the permissions you give it, and every step is written in the audit trail. You never paste a key or a password into a chat.

## Connect it

Open **Use your own AI too** in Pilotie, copy the address, add it as a connector in your AI and sign in. See [use your own AI too](/docs/use-your-own-ai/).

## How an outside AI sees it

Behind the connector the AI gets one tool per app. Each tool takes a `tool` (the part of the app) and an `action` (the verb). The built-in helper uses the same tools through the same door, and you never type any of this.

```json title="What an outside AI sends"
{ "tool": "approval", "action": "new", "args": {} }
```

## A first ask

```text title="A first ask"
Read the project "Studio Lina" and tell me where we are. Then draft the invoice for the website work. Do not send anything.
```

The AI reads the project, drafts the invoice and puts the email in Approvals. You open it, edit it and approve.

## The tools

::mcp-tools

Ask for the actions of a tool with `action: "help"`, and for one action’s arguments with `action: "help"` and `of`. There is one more tool for each app you install.

## Habits that work

- **Name the project once.** "This is for Studio Lina". The AI keeps it in mind from the workspace, not from the chat.
- **Ask it to read first.** "Read the project and tell me where we are."
- **Check the approval.** Open it, read exactly what will happen, then approve.
- **Give each agent a job.** One for the website, one for the books.

## What an outside AI cannot do

It cannot approve its own work: only a person decides an approval. It cannot do what you did not give its agent permission for, and it cannot hide a step: the audit trail keeps them all.