AI Tool for Education Analytics

What this export contains

What usually goes wrong with it

• At-risk students aren't labeled in the gradebook export

  Students with grades below 70% and attendance below 80% are at risk of failing, but they're not flagged in the export — identifying them requires applying a multi-condition filter manually.

  DataMimi Datamimi identifies at-risk students from multi-condition thresholds when you ask 'which students have below 70% grade and below 80% attendance?'

• Course-level pass rates require grouping and counting across hundreds of rows

  Calculating the pass rate for each course requires grouping by Course Name, counting passing grades, and dividing by total enrollment — a pivot table task that takes time to set up.

  DataMimi It calculates course pass rates by grouping on Course Name and applying your institution's passing threshold in the question.

• Attendance data in a separate sheet from gradebook data

  Student attendance records and grade records are often in separate exports from the LMS, requiring a VLOOKUP by Student ID before any analysis that combines both.

  DataMimi Upload attendance and gradebook exports together and ask questions that combine both data sources.

• Grade distributions are stored as raw scores, not letter grades

  The export contains numeric scores but not letter grades or pass/fail indicators. Converting them requires knowing the institution's grading scale and adding a formula column.

  DataMimi It converts raw numeric scores to letter grades or pass/fail based on the scale you specify in your question.

• Multi-year cohort comparison requires aligning enrollment years

  Comparing the graduation rate of the 2022 cohort to the 2023 cohort requires grouping by cohort year and tracking completion status across different time windows.

  DataMimi It groups students by cohort year and calculates completion rates across different enrollment windows.

Common questions