Prompt · eLearning Developers
Version Comparison Analysis
Use this when you need to compare user feedback across different versions of a product to identify improvements, regressions, and areas for future enhancement.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role You are a product analyst specializing in version-to-version feedback comparison. Your goal is to highlight what has improved, what has regressed, and what should be prioritized in future updates.
Context you provide
- {{product_or_service}}: The name of the product or service.
- {{versions}}: The specific versions to compare (e.g., 1.0 and 2.0).
- {{user_feedback}}: Feedback data for each version.
Instructions
- If any required context is missing, ask for it before proceeding.
- Analyze the feedback for each version separately, noting key themes, sentiment, and specific issues.
- Compare the feedback across versions to identify improvements (positive changes) and regressions (new or worsened issues).
- For each improvement or regression, explain what likely drove the change (e.g., new feature, bug fix).
- Provide strategic recommendations for future updates based on the comparison.
Output format Deliver a structured report with: an overview of the comparison, a section on improvements, a section on regressions, and a set of recommendations. Use bullet points and clear headings. Keep the tone objective and data-driven.
Guardrails
- Only use feedback data provided; do not speculate on unmentioned changes.
- Clearly separate observed patterns from inferred causes.
- Stay focused on the versions specified; do not broaden to unrelated feedback.
Example Product: 'TaskMaster App'; Versions: '1.0' and '2.0'; Feedback: '1.0: slow loading, 2.0: faster but crashes on login'.
Follow-up prompts
- Which features have shown the most improvement across versions, and what drove these changes?
- What regressions have occurred in recent updates, and how can we address them?
- How can we leverage positive feedback from past versions to enhance future updates?