> For the complete documentation index, see [llms.txt](https://docs.ebrain.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ebrain.ai/chatting-with-tim/commands-and-mentions.md).

# Slash commands and mentions

For everyday requests you never need special syntax. Just tell Tim what you want in plain language and he handles the rest. The one shortcut worth knowing is the slash (`/`) menu, which lets you run one of your **Agents** directly from the chat box.

{% hint style="info" %}
There is no fixed list of slash commands to memorize. Your slash commands **are your Agents**: whatever Agents exist in your workspace show up in the `/` menu. The list is different for every workspace and changes as you build new Agents. Learn more in [What are Agents?](/agents-autonomous/overview.md)
{% endhint %}

## Running an Agent with `/`

Start a message with `/` to open the Agent picker. As you keep typing after the slash, the list filters down to matching Agents; a space (or picking an item) closes it.

| What you type                     | What happens                                                          | Example                            |
| --------------------------------- | --------------------------------------------------------------------- | ---------------------------------- |
| `/`                               | Opens the Agent picker showing the Agents available in your workspace | `/`                                |
| `/<part of a name>`               | Filters the list to Agents whose name matches what you typed          | `/weekly`                          |
| `/<agent-name> your instructions` | Inserts the command into the box so you can add instructions and send | `/<agent-name> focus on last week` |

When you pick an Agent, `/<agent-name>` drops into the message box. Type any extra details after it, then send. Tim runs that Agent using your typed instructions.

### Keyboard and mouse

The picker works with either:

| Action                    | Key              |
| ------------------------- | ---------------- |
| Move up / down the list   | Up / Down arrows |
| Insert the selected Agent | Enter or Tab     |
| Close the picker          | Escape           |
| Select an Agent           | Mouse click      |

## What the picker shows

Each row in the menu shows the Agent's command name as `/name` (sometimes with a small icon) and a one-line description of what it does. The list is grouped into two sections:

* **Your skills** - the Agents you or your workspace created, sorted by how often you use them.
* **Supplied by eBrain** - built-in Agents that come ready to use.

If nothing matches what you typed, you'll see **No skills found.**

{% hint style="info" %}
Running an Agent from the slash menu always uses Tim's thorough, deeper path so the Agent has the full set of tools it needs, even if your mode is set to Quick. For that turn, Tim follows the Agent's own instructions instead of his normal routing. See [Instant vs thinking mode](/chatting-with-tim/thinking-and-specialists.md).
{% endhint %}

## What about @mentions?

The chat box does not use `@mentions`. You don't need to tag people, accounts, or files with a special symbol.

Instead, just name people naturally in your request. If you write "email Jan about the proposal," Tim figures out who Jan is by searching your mail and calendar. The same goes for accounts, meetings, and documents: describe them in plain words and Tim looks them up for you.

{% hint style="success" %}
You can state facts as ground truth. If you tell Tim "Jan always emails from that address," he treats it as fact and uses it directly, no `@` needed.
{% endhint %}

## Related

<table data-view="cards"><thead><tr><th>Title</th><th data-card-target data-type="content-ref">Link</th></tr></thead><tbody><tr><td>What are Agents?</td><td><a href="/pages/2FNhAcz3vH2jDMbaMGkQ">/pages/2FNhAcz3vH2jDMbaMGkQ</a></td></tr><tr><td>Building an agent</td><td><a href="/pages/GgvpNGdjSwwyImG7i7cp">/pages/GgvpNGdjSwwyImG7i7cp</a></td></tr><tr><td>Files, uploads, and voice</td><td><a href="/pages/Rk6PGIrlfPH7gyqW2G4g">/pages/Rk6PGIrlfPH7gyqW2G4g</a></td></tr><tr><td>Instant vs thinking mode</td><td><a href="/pages/u5sAaqcitd3pbhveNUgq">/pages/u5sAaqcitd3pbhveNUgq</a></td></tr></tbody></table>


---

# 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://docs.ebrain.ai/chatting-with-tim/commands-and-mentions.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.