User Interface
Data Dashboard
The Data Dashboard is the central page where you can ask natural language questions about your data and get the SQL queries generated by PowerBuddy for Data Analysis. You can also write your own SQL queries and get the data for analysis.
The Running status appears at the top of the page to indicate that the app is actively loading content or suggestions. Wait for the content to fully load before taking any actions. Once the Running status disappears, you can proceed with your actions. Do not click Stop, as it may require the processing to restart, potentially leading to longer processing times or errors.
AI-generated queries
Choose a product from the Select a Product menu.
Enter a domain name in the Select a Domain field. Refer to the list of current domains.
In the chat field, enter a question using natural language, then click Get Results. The AI-generated query appears in the SQL Generation section, and in the Edit & Save SQL section where it can be modified if needed. The results appear below the Edit & Save SQL section.
Click Download CSV to save a copy of the results.
To generate a new SQL query and results, click Clear Chat, then enter a new question and click Get Results.
Save SQL
In the Edit & Save SQL section, enter a query name to add tags or a short name to your saved queries.
Review the AI-generated user query in the User query field and update it as needed.
Review the SQL query in the SQL field. You can also edit the SQL query. If you make any modifications, make sure that the user query associated with the modified SQL query is still relevant, then click Save SQL.This ensures that you can access and retrieve the queries without having to regenerate it. When a question closely matches a saved user query in terms of similarity, PowerBuddy retrieves the saved SQL and produces corresponding results. This feature is especially useful for frequently used or complex queries.
Guidelines for writing natural language questions
PowerBuddy for Data Analysis is designed to work well with questions in a natural, conversational manner. You are encouraged to naturally converse with PowerBuddy using the chat to interact and clarify your questions.
Asking specific questions ensures more accurate and relevant responses. PowerBuddy for Data Analysis performs well when provided with clear and well-defined input.
Wherever possible, including timeframes or specific conditions in your questions can help narrow the scope of the response. Providing exact timeframes ensures more accurate responses.
Break down complex questions into smaller parts for PowerBuddy for Data Analysis to comprehend and respond effectively.
Separate multiple inquiries into distinct questions. Asking one question at a time ensures clearer responses and avoids confusion.
If the response contains duplicates, explicitly ask a follow-up question to remove duplicates as needed.
Analysis Hub
The Analysis Hub page provides options to further analyze the data that has been retrieved. You can explore various analytical functionalities including statistics, chart creation, basic machine learning predictions, chart creation, and more.
Additionally, the Analysis Hub offers you suggestions on the types of analysis that can be performed on the fetched data.
Analyze data using AI-generated suggestions
Choose an AI-generated suggested analysis prompt. You can also click Get New Suggestions to generate new suggestions to choose from.
Click Analyze Data.
Analyze data using descriptive language
Enter your own analysis description in the field provided.
Click Analyze Data.
Conclusion
The Conclusion page provides insights and suggestions from the analysis of the data. You can ask questions about the analysis on this page.
Enter your descriptive question about the data displayed on the page.
Click Get Insights. The insights and suggestions for further analysis appear on the page.
Charts cannot be interpreted by PowerBuddy for Data Analysis, and it cannot provide suggestions based on visual representation. The capacity is limited to the underlying data in the tables.
Saved Queries
The Saved Queries page displays the list of all queries saved on the customer account. These are specific to each domain.
The Search field can be used to find any saved query based on keywords from the saved query name or user query. The search results display a list of saved queries that has high similarities with the keyword you entered.
The Saved query name, User query and SQL query will be populated in the Edit & Save SQL section of the Data Dashboard page when you click Load. Click Delete to remove the saved query.