> For the complete documentation index, see [llms.txt](https://docs.artific.nl/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.artific.nl/en/for-administrators/assistants.md).

# AI assistants

Everything an administrator needs to build, configure and maintain assistants.

An assistant is a chat-based helper with a fixed job. You give it a name, a short description, written instructions describing how it should behave, and access to the knowledge and tools it needs. From then on, anyone you give access to can hold a conversation with it.

A well-built assistant is narrow. "Answers questions about our HR policies from the staff handbook" produces far better results than "knows everything about the company". If you need to cover several areas, build several assistants and let one delegate to the others. See [Sub-agents](/en/for-administrators/assistants/sub-agents.md).

## The pieces of an assistant

| Piece                     | What it does                                                               | Where you set it                                                                    |
| ------------------------- | -------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- |
| Identity and instructions | Name, short description, the written instructions that shape its behaviour | [Settings](/en/for-administrators/assistants/settings.md)                           |
| Messages                  | Opening message, tone of voice, creativity                                 | [Settings](/en/for-administrators/assistants/settings.md)                           |
| Knowledge                 | The documents it can draw on when answering                                | [Knowledge and sources](/en/for-administrators/assistants/knowledge-and-sources.md) |
| Tools                     | Actions it can perform, like looking something up in another system        | [Tools](/en/for-administrators/assistants/tools.md)                                 |
| Connectors                | Access to actions on external servers                                      | [Connectors](/en/for-administrators/assistants/connectors.md)                       |
| Suggested questions       | The starter prompts a user sees on an empty chat                           | [Suggested questions](/en/for-administrators/assistants/suggested-questions.md)     |
| Appearance                | Colours, logo and shape of the chat window                                 | [Themes](/en/for-administrators/assistants/themes.md)                               |
| Access                    | Which user groups may use it                                               | [Advanced settings](/en/for-administrators/assistants/advanced-settings.md)         |
| Assurance                 | Automated checks that it keeps answering correctly                         | [Quality control](/en/for-administrators/quality.md)                                |

## The usual order of work

1. **Create it.** Name, short description and opening message: three fields, thirty seconds. See [Creating an assistant](/en/for-administrators/assistants/creating-an-assistant.md).
2. **Write the instructions.** This is where most of the quality comes from. See [Settings](/en/for-administrators/assistants/settings.md).
3. **Give it knowledge.** Attach the collections or search tools it should draw on. See [Knowledge and sources](/en/for-administrators/assistants/knowledge-and-sources.md).
4. **Try it.** The **Preview** tab shows exactly what a user will see. See [Preview and embedding](/en/for-administrators/assistants/preview-and-embedding.md).
5. **Open it up.** Set which user groups may use it, then turn on **Assistant visible to users**.
6. **Keep it honest.** Add quality control scenarios so you find out when an answer drifts. See [Quality control](/en/for-administrators/quality.md).

{% hint style="info" %}
An assistant stays invisible to users until **Assistant visible to users** is switched on. You can build and test in peace before anyone sees it.
{% endhint %}

## The assistant overview

**AI assistants → Assistants** shows every assistant you can see, as cards. Users can star an assistant to pin it to a **Favorite assistants** row at the top; everything else appears under **Other assistants**. A disabled assistant is greyed out.

The **⋮** menu on each card is the administrator's shortcut into **Settings**, **Tools**, **Quality control**, **Embed** and **Delete**. Which of those you see depends on your rights.