> For the complete documentation index, see [llms.txt](https://docs.growthfactor.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.growthfactor.ai/getting-started/home.md).
# Home
Home is the first thing you see after logging in. It opens on a greeting and the question **Where are we growing today?** Click **Home** at the top of the sidebar, or the GrowthFactor logo, to come back to it from anywhere.
***
## Search
Type into the search bar to start new work. The placeholder text rotates through example prompts, such as an address search or a question for the agent. It stops rotating while you click into the bar or type, and it stays still if your device is set to reduce motion. A dropdown opens under the bar as you type, and every row it offers creates a new study.
* **An address** — Matching places appear as suggestions. Click one, or press `Enter` to take the top match. The new study is named after the address and opens with a pin dropped there and a trade zone generated from your workspace's default. The pin comes up selected, so its panel is already open. The agent panel starts collapsed so the map has the room. Click the collapsed agent pill to expand it. Coordinates like `40.7128, -74.0060` get an **Analyze** row instead of suggestions.
* **Ask the agent** — Opens a new study and sends what you typed as the first message to the [GrowthFactor Agent](/study/growthfactor-agent.md).
Which row `Enter` takes depends on what you typed. Anything phrased as a question, or a request longer than a few words, goes to the agent. A short phrase that matches a place goes to the address. Use the arrow keys to override the highlighted row.
Search (shortcut `/`) can be jumped into from anywhere on the Home page.
{% hint style="info" %}
Addresses are looked up before the study is created, so a lookup that comes back empty says **Couldn't find that address** and leaves no empty study behind. Picking a named business or landmark names the pin after it rather than its street address.
{% endhint %}
***
## Quick Actions
Below the search bar:
* **New study** opens a blank study.
* **All studies** opens the full studies list.
* **Deal dashboard** opens your pipeline.
***
## Starred
When you have starred studies, a **Starred** list appears below quick actions. It shows up to three of them, with the one you edited most recently first and when you last touched it. A starred study you've never edited is ordered by when it was created. Click one to open it. See [Starring](/study/overview.md#starring).
***
## Where You Left Off
**Where you left off** lists up to three studies you've edited most recently, newest first, with when you last touched each one. Click one to jump back in. Starred studies appear in **Starred** instead. Studies you've never edited yourself don't appear, and the section stays hidden until you have one.
When both lists have studies, they sit side by side. If either list can't load, it shows **Couldn't load your studies.** with a **Try again** link.
---
# 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.growthfactor.ai/getting-started/home.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
