Best practices for working with PowerBuddy for Data Analysis
Be specific
If you want specific details of a student, instead of entering the full name in the question specify the first name and last name of the student.
For example, ask PowerBuddy for Data Analysis this question:
Provide attendance records of student with first name Antonio and last name Rojas.
You can also ask to include their student ID.
If you are aware of the specific column name or the values it might have, you can also include it in your question.
For example, you can ask PowerBuddy for Data Analysis to show the student count for PRESENCE_STATUS_CD for daily attendance or you can ask it to list all attendance records between Jan 2024 and Jun 2024 where attendance mode is ATT_ModeDaily, grouped by attendance code description and ATT_DATE.
Refer to the PowerSchool SIS Data Dictionary for more information on data descriptions.
Providing specific information, helps PowerBuddy for Data Analysis to understand exactly what is needed, reducing ambiguity and improving the accuracy of results.
There can be multiple ways to write queries. If you are expecting the generated query to use table A and table B, but if it uses table A, table C, and table D, specify your preference of using tables A and B for the query. Although the generated query might be right, specifying your preferred table will generate a query in the way you need it.
Provide specific conditions or exact timeframes
Instead of asking:
Provide list of students in 12th grade who are absent for more than 5 days in the current academic year
Rephrase the question as:
Provide list of students in 12th grade who are absent for more than 5 days in the current academic year July 2024 to June 2025
Including specific keywords or context such as grade levels or specific demographics narrows down the search scope and ensures the most relevant data is retrieved.
Use natural language
If the response contains duplicates, explicitly ask a follow up question in the chat:
Remove duplicates from the data.
If you're unsure about specific information, engaging in a chat or conversation can be helpful. This allows you to clarify details, seek guidance, and refine your query for more accurate results.
For example, if you want to retrieve the distribution of historical grades on a particular course, but you are uncertain about the exact course number or course name, you can ask PowerBuddy for Data Analysis:
Get a list of available courses with course numbers.
Once you get the exact course number and course name, you can refine the query accordingly and ask PowerBuddy for Data Analysis:
List the distribution of historical grades in each term for English 9 with course number ENG100.
Modifying prompts
You can rephrase a question if the generated SQL query does not provide the expected results. Chat with PowerBuddy for Data Analysis to make any modifications to the prompt pr question.
For example, if you ask PowerBuddy for Data Analysis:
What is the overall trend in incidents reported between Jan 2023 and Dec 2023, grouped by school names?
After the results are retrieved and you decide you want to update the timeframe, you can enter a follow-up prompt:
Update the timeframe as June 2023 to Dec 2023.
Updating the prompt this way makes the necessary changes on the generated SQL query.