> 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/thinking-and-specialists.md).
# Instant vs thinking mode
Some questions deserve a quick answer. Others need real digging. Tim handles both, and you can let him decide or steer it yourself.
## The two ways Tim answers
When you ask Tim something simple, like a quick lookup or a single action, he answers fast in one shot. When you ask something harder that spans several steps, people, or sources, he takes more time to work through it thoroughly. The trade-off is simple: speed for easy things, depth for complex ones.
## Choosing a mode
You set the mode from the selector at the bottom-left of the message box, labeled **Tim 1.4**. There are three choices:
| Mode | Description | Best for |
| ------------ | -------------------------------- | ---------------------------------------------------------------------------------- |
| **Auto** | Adapts per question | The default. Tim decides per question whether to answer fast or think more deeply. |
| **Quick** | Immediate response | Fast, single-shot answers for simple lookups and quick actions. |
| **Thorough** | Takes time for complex questions | Deep, multi-step analysis and research spanning several people or topics. |
{% hint style="info" %}
Your choice is remembered between sessions. When you pick **Quick** or **Thorough**, its label shows next to **Tim 1.4** in the message box. Leave it on **Auto** and Tim adapts on his own.
{% endhint %}
In **Quick** mode, Tim uses his own search and action tools and answers directly without bringing in specialists. In **Thorough** mode, he has his full toolset and can run focused specialist helpers in parallel to cross-check sources and be comprehensive.
## What the specialist steps mean
In Thorough mode, you may see Tim bring in focused helpers for different kinds of work. This is normal. He is delegating parts of the job to specialists so each piece gets proper attention, for example:
* **Research** for deep, multi-source investigation
* **Email** for mail-related work
* **Tasks** for projects and to-dos
* **Planning** for working things out step by step
You will see this summarized in a **Team activity** panel with a title, a **What Tim did** narrative, and an **Activity** breakdown grouped by helper, each with an action count (for example, "3 actions"). You can expand or collapse it, and these runs are saved so you can review them later.
## Watching progress
You never have to sit and wait blindly. While Tim works, a live status line shows what he is doing, and each step appears in plain language as he goes, with a spinner while it runs and a check when it finishes. When Tim reasons through something, you can expand a **Show reasoning** toggle to see a summary of his thinking. Everything is collapsible, so the final answer stays clean.
{% hint style="success" %}
Running an Agent with a slash command always uses the thorough path, because it needs the full toolset, even if your mode is set to Quick. See [Slash commands and mentions](/chatting-with-tim/commands-and-mentions.md).
{% endhint %}
## What stays the same in both modes
The mode only changes how deeply Tim works. It never changes the safety rules:
* Tim still asks before any write. Sending an email, creating an event, or changing a task always waits for your approval. See [Approval flows explained](/chatting-with-tim/approval-flows.md).
* You can stop a response at any time, and anything Tim already wrote stays visible.
---
# 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/thinking-and-specialists.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.