> 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/ai-corpus.md).

# AI Corpus

An **AI Corpus** is a themed knowledge base. Each Corpus groups structured, reliable and controlled content so the assistant gives coherent, relevant answers aligned with your organisation. This is the heart of Verbatim AI — the clearer and more complete your Corpus are, the more the AI becomes a true expert of your business.

![Your Corpus are collaborative](/files/clbYY60WcpPm7fGtWhns)

## The Corpus space

Open the **Corpus** space to manage all your Corpus. Each one is shown as a card representing a specific domain of knowledge — for example:

* **Sales** — sales techniques, talking points, best practices
* **Marketing** — strategies, resources, processes, internal references
* **Legal** — contracts, policies, regulatory texts
* **Project** — everything about one project, so your project managers get their own assistant

Create as many Corpus as you need to structure your knowledge. Tap the **➕** button at the bottom-right to create a new one.

> 🔐 **Secure and partitioned.** Data stays specific to each Corpus. The assistant only uses the documents placed inside that Corpus's environment, so you keep full control over what is accessible.

## Create an Corpus ✨

When you create an Corpus, you define:

* **A name** — visible to you and to collaborators with access. Choose something that makes the field of knowledge obvious at a glance. 💫
* **A personality** — pick one of the six [personalities](/docs/profile.md) so the Corpus's tone reflects its domain.
* **A description** — in a few words, set the context: project presentation, area of expertise, activity…

> 💡 **Organise by area of knowledge.** One Corpus for Marketing (product sheets, guidelines, personas…), one for Legal, one per project… Keep each Corpus focused and it stays sharp.

## Inside an Corpus 💁‍♀️

Opening an Corpus brings together everything that powers it:

* **Your Stories** — chat with the Corpus to query its knowledge. The most recent conversations appear under **Latest stories**; all of them are also available from the main [**Story**](/docs/stories.md) screen.
* **Latest files** — the most recent [documents](/docs/documents.md) added to the knowledge base. Tap **See more** or the 📎 icon (top-right) to see them all.
* **Your team** 👥 — share the Corpus with collaborators for a truly collaborative experience.
* **Connectors** ⚡ — synchronise the Corpus with sources like Google Drive or SharePoint so documents flow in automatically ([Pro Edition](/docs/pro-edition.md)).
* **Deployment** ✈️ — deploy the Corpus into Slack or Teams to query it right from your channels ([Pro Edition](/docs/pro-edition.md)).

## Update an Corpus ✨

Need to change something? Open the Corpus and edit its **name**, **personality** or **description**.

> 🔥 Don't forget to click **Save** at the bottom of the page to confirm your changes.

## Delete an Corpus 🗑️

Is an Corpus obsolete — a finished project, or a knowledge base you no longer use? Use the **Trash** icon at the top-right of the Corpus screen.

> ⚠️ **This deletion is definitive.** The Corpus and all of its documents are permanently removed and cannot be restored. Double-check you've selected the right Corpus before you confirm.


---

# 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/ai-corpus.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.