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

# Welcome to Verbatim AI

**Verbatim AI turns your documents into a private, reliable AI assistant.**

Instead of endlessly searching through files, you simply drop your documents into a workspace and let your **AI Corpus** do the rest: it reads, analyses, understands and answers your questions — relying **exclusively on your own knowledge**, and naming the documents it used.

![Your AI Corpus relies on your own knowledge base](/files/FeoUaXFfF67JxaFuYBMq)

## What Verbatim AI does for you

* 🗂️ **Organize your knowledge into Corpus.** Each Corpus is a themed knowledge base (Sales, Marketing, Legal, a project…) that answers with your vocabulary and your context.
* 🔋 **Feed it your documents.** Upload PDF, Word and PowerPoint files, or synchronise folders from Google Drive, SharePoint, OneDrive and more.
* 💬 **Just ask.** Start a **Story** (a conversation) and get precise answers grounded in your data, with the source documents cited.
* 👥 **Work as a team.** Share your Corpus with colleagues, each with their own access rights.
* 🔐 **Stay in control.** Your data is private, hosted in Europe, never shared and never used to train third-party models.

Verbatim AI is built on a robust and secure **Retrieval-Augmented Generation (RAG)** architecture, so your assistant stays competent, reliable and grounded in the truth of your own documents.

## Need help ?

Get help from our team just by filling our [**Helpdesk form**](https://2f5q5a.share-eu1.hsforms.com/262M2Y1wOTw2glc_LAp_cQg). Helpdesk team will be back to you shortly.

***

## 📖 Table of contents

Use this guide to discover each feature step by step.

| Guide                                                  | What you'll learn                                                          |
| ------------------------------------------------------ | -------------------------------------------------------------------------- |
| 🧭 [Getting started](/docs/getting-started.md)         | Create your account, activate your free trial and take your first steps.   |
| 🏠 [The dashboard](/docs/dashboard.md)                 | Read your activity at a glance and resume your latest ideas.               |
| 😎 [Your profile & AI personalities](/docs/profile.md) | Tell your Corpus who you are, pick a personality and secure your account.  |
| ⭐ [AI Corpus](/docs/ai-corpus.md)                      | Create, customise and manage your themed knowledge bases.                  |
| 📄 [Documents](/docs/documents.md)                     | Add, replace, rename, download and delete the files that fuel your Corpus. |
| 📚 [Stories](/docs/stories.md)                         | Chat with your Corpus, get sourced answers and export your work.           |
| 🔑 [API keys](/docs/api-keys.md)                       | Publish RSA keys to call the secured Verbatim AI API.                      |
| ✨ [Pro Edition](/docs/pro-edition.md)                  | Unlock connectors, Slack/Teams, collaboration and more.                    |

***

## The 4 steps to get value, fast

1. [**Fill out your profile**](/docs/profile.md) so your Corpus knows who you are. 😎
2. [**Create your first AI Corpus**](/docs/ai-corpus.md) and give it a name and a personality. 🚀
3. [**Feed your Corpus**](/docs/documents.md) with the documents it needs to work on. 🔋
4. [**Start a Story**](/docs/stories.md) and ask your first question. 🔊

Ready? Head over to [**Getting started**](/docs/getting-started.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, and the optional `goal` query parameter:

```
GET https://verbatim-ai.gitbook.io/docs/home.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.