Professional Context
I still remember the frustrating moment when I had to spend an entire weekend grading a stack of exams, only to realize that I had to re-grade them all because of a misinterpretation of the rubric. It was then that I wished I had a more efficient way to analyze student performance data and identify areas where my students needed extra support.
💡 Expert Advice & Considerations
Don't bother trying to use Gemini to automate your lesson plans, just use it to help you make sense of the never-ending spreadsheets of student data.
Advanced Prompt Library
4 Expert PromptsAutomated Student Progress Tracking
Create a Google Sheets template that can automatically track student progress across multiple assignments and exams, using a weighted average formula to calculate overall grades. The template should include conditional formatting to highlight students who are at risk of falling behind, and a separate tab for notes on individual student progress. Assume a class size of 25 students and 5 assignments per semester.
Data-Driven Lesson Plan Optimization
Analyze a dataset of student performance on a specific standardized test, and use the results to identify areas where the current lesson plan is falling short. Provide recommendations for targeted interventions and adjustments to the lesson plan, including specific resources and activities that can be used to support student learning. The dataset should include demographic information, test scores, and teacher observations.
Google Classroom Workflow Automation
Design a workflow that automates the process of creating and grading assignments in Google Classroom, using Google Apps Script to generate grading rubrics and feedback templates. The workflow should include notifications to students when assignments are posted or graded, and automatic reminders to teachers when assignments are due. Assume a class size of 30 students and 10 assignments per semester.
Student Performance Prediction Modeling
Develop a predictive model using Google Cloud AI Platform that can forecast student performance on upcoming exams, based on historical data on student grades, attendance, and demographic information. The model should include variables for teacher effectiveness, school resources, and community support, and provide recommendations for targeted interventions to support at-risk students. Assume a dataset of 500 students and 5 years of historical data.