> 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/getting-started/meet-tim-and-donna.md).
# Meet Tim and Donna
eBrain comes with two assistants who do very different jobs. **Tim** is the one you talk to. **Donna** is the one who sits in your meetings. They work together: Donna captures what happens in your calls, and Tim can search and reason over those notes whenever you ask.
This page introduces both, and clears up one thing people often mix up: the difference between chatting with Tim and setting up an autonomous **Agent**.
## Tim, your AI assistant
Tim is your right-hand AI colleague. You talk to him in plain language and he handles the rest, across your whole workspace. The Chats page greets you with **"Talk to Tim"** and the invitation: *"I help you think, decide, and get work done. Ask in plain language, I will handle the rest."*
Tim is not a narrow email bot or a bookkeeping tool. He is a general-purpose chief of staff who can:
* **Read and act on your mail** across all connected mailboxes (Gmail and Outlook, multiple accounts) - searching, summarizing, and drafting replies.
* **Manage your calendar** - check availability, read your agenda, and create, update, or delete events.
* **Run your tasks and projects** - list, create, update, assign, and comment.
* **Use Donna's meeting notes** - search and reason over transcripts and summaries.
* **Search the web** for anything current, and run **deep research** across your mail, calendar, contacts, documents, and meeting notes.
* **Remember** facts, preferences, and decisions long-term, so you never have to repeat yourself.
A few things make Tim different from an ordinary chatbot:
{% hint style="info" %}
**He always asks before acting.** Tim never sends an email, changes your calendar, or edits a task without your say-so. When he wants to make a change, he shows you an approval card with the details and waits for you to confirm or reject it. Reading and searching happen freely; writing always needs a click.
{% endhint %}
* **He's proactive.** He keeps an eye on your inbox, calendar, and tasks and reaches out when something genuinely needs you - not only when asked.
* **He remembers.** Long-term memory carries across conversations.
* **He delegates.** For bigger jobs he hands work to specialist agents behind the scenes and brings the results back to you.
You reach Tim two ways: on the web through the **Chats** page, and on **WhatsApp**. It's the same Tim either way.
## Donna, your meeting notetaker
Donna is eBrain's AI notetaker. She joins your online video meetings as a visible participant, listens, and afterwards gives you a **full transcript** plus **AI-written notes** - a summary, key points, and action items. She works with Google Meet, Microsoft Teams, and Zoom.
You can have Donna join automatically (she scans your connected calendar and shows up for qualifying meetings), or add her to a specific call yourself. Recording is audio-only - no video is ever stored. Once she's done, you'll find everything on the **Meetings** page, and Tim can search those notes for you on request.
## Tim and Donna at a glance
| | **Tim** | **Donna** |
| ---------------- | ---------------------------------------------------------- | -------------------------------------------------------- |
| **Role** | The assistant you talk to | The meeting notetaker |
| **Where** | Chats page and WhatsApp | Joins your online meetings; results on the Meetings page |
| **What you do** | Ask in plain language | Invite her, or let her auto-join |
| **What you get** | Answers, drafts, actions (with your approval) | Transcripts and AI notes after each call |
| **Works with** | Mail, calendar, tasks, research, memory, and Donna's notes | Google Meet, Microsoft Teams, Zoom |
## Tim in chat vs. Agents
There's one more distinction worth knowing early. Talking to Tim is a **live, back-and-forth conversation**: you're present, and he asks for your approval before any write action.
An **Agent** is a chat with Tim that you've **saved so it runs on its own** - on a schedule (say, a morning brief every day at 8:00) or whenever you press a button. Because nobody is in the room to answer questions or approve a step, an Agent runs in read-only mode: it gathers and analyzes your information and produces a result - a briefing, a summary, a draft, a list of what needs attention - and delivers it to you to review and act on. Agents don't send email or create events on their own.
{% hint style="info" %}
**Rule of thumb:** chat with Tim when you want something done now, with you steering. Build an Agent when you want the same job done automatically, again and again.
{% endhint %}
## Where to go next
---
# 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/getting-started/meet-tim-and-donna.md?ask=
```
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.