# Step 1: Definition & Collection
After clicking on "New RAT Study", you can first give your study a name and description that will be useful to you.
In the next step, you can download the RAT Browser Extension for Google Chrome. The "Guide" button will assist you with the installation process.
After opening the extension, you can create a “New Study Session”. You can also save existing study sessions by using the "Backup All" button and restore them with the "Restore" option. Since the browser extension is installed locally, this feature is particularly useful when switching devices. Additionally, you can manage or add new scrapers in this section.
In the new session, you can assign a name to it and you can specify the set of search queries. To do this, you can either enter the search queries manually, upload a CSV or TXT file containing your search queries, or utilize the [**Query Sampler**](/result-assessment-tool-rat-docs/the-query-sampler.md).
Now you can indicate how many search results RAT should gather per query. Afterwards choose the search engines or systems and in which countries and languages you want the RAT to collect results. For example, you can choose to collect results from the English language version of Google in the United States. Optionally, you can also add a more specific location, e.g. city or region.
Ultimately, you need to decide if you want to save the screenshots and HTML files of the search engine result pages (SERPs), as this can consume a lot of storage space. You also have the option to configure some Advanced Settings here.
After creating the session, you can update your settings if necessary and begin collecting the results. During this process, RAT is collecting the metadata of the search results and AI responses and you can easily monitor the “Status” and “Activity log”. Once the collection is complete, click on the “Download Results (ZIP)” button to export all the data that RAT has collected.
Back In the web interface of RAT, you can now upload the ZIP file that you downloaded from the browser extension. By uploading this file, RAT will automatically begin downloading the screenshots and HTML files of the search results, which you can monitor in real time. Below, you will find a summary of all the data that RAT has collected.
If you don't require screenshots and HTML files of the search results for your analysis or for human assessment, you can use the "Live Link Mode." This mode disables background scraping, allowing participants to visit the live URLs directly in the assessment interface later.
---
# Agent Instructions: 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://result-assessment-tool-rat.gitbook.io/result-assessment-tool-rat-docs/what-is-rat-and-how-does-it-work/step-1-definition-and-collection.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.