> For the complete documentation index, see [llms.txt](https://docs.gaiodataos.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.gaiodataos.com/tools/discovery/power-search.md).
# Power Search
Gaio Power Search is a remarkable feature that significantly simplifies the availability of data for all employees in a company. With high ease of creation and use, users can access this functionality from the Gaio Platform’s home screen and naturally type in the terms they wish to search. Gaio will automatically create data visualizations with charts that best demonstrate the results of the query, making information exploration a quick and efficient task.
***
## **How to Use**
***
### **1. Access the Power Search task**
* In the **Studio**, go to the Delivery panel.
* Click on plus button.
***
### **2. Configure Basic Info**
* **Label**: Add a name for the task to identify it context.
* **Table Name:** choose the table that will serve as your data source (e.g., `sales`).
* **Description** *(optional)*: helpful text to clarify the meaning of the table.
* **User filter column** *(optional)***:** field to apply automatic filters based on the logged-in user (e.g., `region` or `sales_rep`).
* **Search**: search columns of your table.
***
### **3.Configure the Fields**
For each column in the table, you can configure:
* **Field Type** (icon on the left):
* `Value`: for categorical or text fields
* `Sum`: for numeric fields to be aggregated (e.g., units sold)
* `Month`: for time-based fields used in timelines
* **Title**: label displayed in generated visualizations
* **Description** *(optional)*: helpful text to clarify the meaning of the field
* **Format**: choose formatting such as Decimal, Currency, Percentage, etc.
***
### **4. Save the Configuration**
* Click **Save** in the top-right corner to apply your settings.
### **5. Activate PowerSearch**
* After saving, leave the studio and click the **Search** button to enable the AI-powered search interface or click in Ctrl+G.
***
#### Best Practices
* Use **friendly and descriptive names** for fields (e.g., “Order Date” instead of “order\_dt”)
* Always add **descriptions** to help users understand each field
* Format numeric fields clearly — such as setting them as Decimal or Currency
* **Remove unnecessary fields** to simplify and optimize search results
* Focus on **aggregatable fields** (like units\_sold, revenue, etc.) for richer insights
---
# 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, and the optional `goal` query parameter:
```
GET https://docs.gaiodataos.com/tools/discovery/power-search.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.