> For the complete documentation index, see [llms.txt](https://planck-ai.gitbook.io/planck-ai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://planck-ai.gitbook.io/planck-ai-docs/documentation/getting-started-1/quick-start.md).

# Quick Start

This guide helps you complete your first useful workflow in Planck AI.

By the end, you should be able to open a workspace, add a document or data source, ask a question, and understand the answer.

### Before you begin

You need:

* Access to a Planck AI account
* Access to at least one workspace
* A document, spreadsheet, CSV file, or connected data source

If you do not see any workspace after logging in, contact your Planck AI administrator.

### Step 1: Open a workspace

After logging in, open the workspace you want to use.

A workspace contains the documents, databases, integrations, users, and conversations for a team or project.

Examples of workspaces:

* Finance
* Operations
* Customer Support
* Network Planning
* Client Project Workspace

### Step 2: Add a document or data source

Depending on your setup, you can work with:

* Uploaded documents
* Excel files
* CSV files
* Connected databases
* Synced cloud storage folders
* SharePoint or OneDrive files

If your workspace is already connected to a data source, you may not need to upload anything manually.

### Step 3: Ask your first question

Open the workspace chat and ask a clear question.

Examples:

```
Summarize this document.
```

```
What are the key numbers in this spreadsheet?
```

```
Show me the largest suppliers by spend this month.
```

```
Which documents mention delayed rollout milestones?
```

### Step 4: Review the answer

Planck AI may return different types of outputs depending on the question and data source.

Common answer formats include:

* Text summaries
* Tables
* Charts
* Code or SQL snippets
* Maps
* Source references or citations

For business-critical work, review the supporting context before taking action.

### Step 5: Continue the conversation

You can ask follow-up questions in the same conversation.

Examples:

```
Break this down by month.
```

```
Show the same result as a table.
```

```
Which rows or documents support this answer?
```

```
What changed compared to the previous quarter?
```

### Step 6: Use the API if needed

Developers can use the Planck AI API to access workspaces, documents, conversations, and chat programmatically.

API keys are created from user settings.

Use the API when you want to:

* Build a custom application
* Automate workflows
* Connect Planck AI to another system
* Create a chatbot or embedded assistant


---

# 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://planck-ai.gitbook.io/planck-ai-docs/documentation/getting-started-1/quick-start.md?ask=<question>
```

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.