> For the complete documentation index, see [llms.txt](https://docs.ovaledge.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ovaledge.com/ai/askedgi/perform-data-analysis.md).
# Perform Data Analysis
## Why Analysis Matters
In many organizations, business teams depend on analysts or data engineers to write SQL queries or build dashboards. This dependency creates bottlenecks and delays, especially for exploratory analysis. Even with direct access to data, non-technical users often struggle to transform raw datasets into actionable insights.
askEdgi eliminates these barriers by enabling natural language analysis directly in the Workspace. Files can be uploaded or catalog objects added, and queries can be expressed in plain language. The assistant responds with text summaries, tables, or visualizations, reducing reliance on SQL scripts or BI tools.
## What Can Be Done
Within the Workspace, askEdgi supports:
* Adding datasets from the data catalog
* Uploading external files (CSV, Parquet up to 100 MB)
* Asking natural language questions about data
* Generating visual outputs such as bar, line, pie, and scatter charts
* Running quick aggregations, filters, and descriptive summaries
### **Use Case & Real-Life Scenario**
A product manager investigating return patterns adds two catalog tables into the Workspace:
* orders
* returns
The manager submits the query:
“**Join orders and returns on order\_id to show total returns by product\_id.**”
askEdgi automatically generates the join and produces a table with aggregated return counts by product.
The following query is:\
“**Create a bar chart of total returns by product.**”
The askEdgi generates a bar chart highlighting two products with the highest return counts.
The analysis continues with:
“**Show return percentage by product category.**”
askEdgi calculates the return ratio versus total orders and provides both a table and a chart. This sequence of queries enables rapid identification of quality issues without SQL or manual dashboard creation.
#### Availability
* Public – Available (file upload, analysis, visualization)
* SaaS – Available (complete analysis capabilities)
* On-Prem – Not available (limited to metadata analytics only)
***
Copyright © 2025, OvalEdge LLC, Peachtree Corners, GA USA
---
# 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.ovaledge.com/ai/askedgi/perform-data-analysis.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.