> 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/overview.md).

# Chatting with Tim

Tim is your right-hand AI colleague. You talk to him in plain language on the **Chats** page, and he handles the work across your whole business: your inbox, calendar, tasks, meeting notes, and research. There is no special syntax to learn. As the Chats page puts it: *"Ask in plain language, I will handle the rest."*

When a chat is empty, Tim greets you with **"How can I help?"** and shows a few starter suggestions so you have somewhere to begin. Just type what you want into the box ("Tell me what you want to do...") and send.

{% hint style="info" %}
Tim is far more useful once your accounts are connected. If you see a **"Connect your tools to put Tim to work"** banner, head to **Settings > Integrations** and link your mailboxes and calendars. See [Connecting your accounts](/account-and-settings/integrations.md).
{% endhint %}

## What Tim can help with

You can ask Tim for any of these in everyday language:

* **Mail** - search across all your connected mailboxes (Gmail and Outlook, multiple accounts), read and summarize messages, and draft replies. When he lists emails, he shows the content and a link to open the message in Gmail or Outlook.
* **Calendar** - check your availability, read your agenda, and create, move, or cancel events. Ask "Am I free tonight?" and he checks before answering.
* **Tasks and projects** - list, create, update, assign, and comment on tasks in eBrain's own [Tasks](/tasks/overview.md).
* **Meetings** - search and reason over the transcripts and notes that Donna produces from your calls, and set up a notetaker. See [Meetings](/meetings-donna/notes-and-transcripts.md).
* **Research** - deep, multi-source investigations across your mail, calendar, contacts, uploaded documents, and meeting notes, plus Dutch legal research. For questions spanning several people or companies, he works through them in parallel.
* **Web search** - for anything current (news, prices, who runs a company right now), he searches the web automatically and trusts fresh results.
* **Reminders** - ask him to nudge you later, and he can reach out at the right time. See [Proactive messages and reminders](/ebrain-on-whatsapp/proactive-and-reminders.md).
* **General help** - answering questions, drafting content, and planning work. For legal or financial matters he gives you the facts to decide and suggests confirming consequential calls with a professional.

Tim always replies in the language you write in, and he looks things up before answering instead of guessing.

## How to phrase requests well

{% hint style="success" %}
**Tips for great results**

* **Just ask plainly.** If your request is clear, Tim acts on it rather than asking you questions back.
* **"Show" vs "do".** Words like *show, find, get, read* make Tim retrieve and display. He only writes (*send, add, create, delete*) when you explicitly ask.
* **Follow-ups work.** "Reply to that one" or "show me the link" refer to what's already on screen - no need to repeat yourself.
* **State facts as truth.** Tell him "Jan always emails from that address" and he uses it directly.
* **He sees one workspace at a time.** Tim reads and writes only your active company's data. To work elsewhere, switch companies in the app.
  {% endhint %}

## Example prompts and what Tim does

| You say                                                 | What Tim does                                                     |
| ------------------------------------------------------- | ----------------------------------------------------------------- |
| "What urgent items need my attention this morning?"     | Reviews your inbox, calendar, and tasks and surfaces what matters |
| "Prep me for today's meetings"                          | Pulls together context for each meeting on your agenda            |
| "Find the latest email from Anna and summarize it"      | Searches your mailboxes and shows the message with a summary      |
| "Reply and say I'll join the call"                      | Drafts an editable reply for you to review and send               |
| "Am I free Thursday afternoon?"                         | Checks your calendar and answers                                  |
| "Schedule a 30-minute call with Sam on Thursday at 3pm" | Prepares the event for your approval                              |
| "Create a task to follow up with the client by Friday"  | Prepares the task for your approval                               |
| "Summarize the notes from yesterday's standup"          | Searches Donna's meeting notes and summarizes                     |
| "Who is the CEO of that company right now?"             | Searches the web and answers with fresh results                   |
| "Research these two suppliers for me"                   | Runs a thorough, multi-source investigation                       |
| "Remember that I prefer morning meetings"               | Saves it to memory for future conversations                       |

## Two things to know up front

{% hint style="warning" %}
**Tim always asks before he acts.** He never sends an email, changes your calendar, or edits a task without your explicit confirmation. Instead of just doing it, he shows you an approval card (or an editable email draft) and waits for you to approve. Read [Approval flows explained](/chatting-with-tim/approval-flows.md).
{% endhint %}

**Tim remembers.** Facts, preferences, and decisions you share carry across conversations, so you don't have to re-explain context every time. See [How Tim remembers things](/chatting-with-tim/memory.md).

**Fast or thorough.** Tim can answer instantly for quick lookups or take more time for complex, multi-step work, and you can steer this with the mode selector. See [Instant vs thinking mode](/chatting-with-tim/thinking-and-specialists.md).

## Keep exploring

<table data-view="cards"><thead><tr><th>Topic</th><th data-card-target data-type="content-ref">Link</th></tr></thead><tbody><tr><td>Run your Agents from the chat box</td><td><a href="/pages/8grULk2Z5jPA2fdHnFLC">/pages/8grULk2Z5jPA2fdHnFLC</a></td></tr><tr><td>Attach files and dictate by voice</td><td><a href="/pages/Rk6PGIrlfPH7gyqW2G4g">/pages/Rk6PGIrlfPH7gyqW2G4g</a></td></tr><tr><td>Folders, pinning, and search</td><td><a href="/pages/8PmCSIMg2jv5746Y6Nq1">/pages/8PmCSIMg2jv5746Y6Nq1</a></td></tr><tr><td>How approvals keep you in control</td><td><a href="/pages/U5I52kkdwBkHiYY8zxEH">/pages/U5I52kkdwBkHiYY8zxEH</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/overview.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.