Analyze course completion, quiz results, and learner feedback
Turns LMS completion data, assessment item results, and survey comments into a diagnosis of what to fix in a course.
The prompt
Analyze the data from my training course and tell me what to improve.
Course and objectives: [NAME and OBJECTIVES]
Completion and drop-off data: [PASTE - e.g. enrollments, completions, where learners exit, time spent per module]
Assessment results: [PASTE - item-level scores if available, attempts, pass rate]
Learner feedback survey results and comments: [PASTE]
Any business or behavior data: [e.g. manager observations, error rates, or "none"]
Analysis steps:
1. Completion: where do people drop off and what is likely causing it (length, relevance, technical issues, mandatory vs. optional)?
2. Assessment item analysis: for each question, difficulty (percent correct) and, if I give enough data, whether high scorers and low scorers differ. Flag items almost everyone gets right (too easy or giveaway), items most get wrong (unclear question, wrong key, or content gap), and distractors nobody picks.
3. Feedback: themes in comments with rough counts and representative quotes. Separate reactions (liked it) from signs of usefulness (will apply it).
4. Connect the dots: where do data sources agree or contradict?
Return:
1. The top 5 findings, each with evidence.
2. A table: Issue | Evidence | Likely cause | Recommended fix | Effort (low/med/high).
3. Questions to answer with more data.
Use only the numbers I give. Do not invent figures. Note where sample sizes are too small to conclude anything.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- NAME and OBJECTIVES
- PASTE - item-level scores if available, attempts, pass rate
- PASTE
- e.g. manager observations, error rates, or "none"
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Group students for intervention from screening and assessment dataSorts students into MTSS or RTI tiers and intervention groups from universal screening and diagnostic results.
- Diagnose where our college admissions funnel is losing studentsAnalyzes inquiry-to-enrollment conversion, yield, and summer melt to find where prospective students drop off.
- Identify the leading and lagging indicators for my business or teamSorts your metrics into leading and lagging indicators, links each lead to the outcome it predicts, and fills gaps in early-warning measures.
- Pick the three insights and five numbers my executives needRanks your findings down to the single most important insight, the top three, the five numbers to watch, and the biggest surprise.