Complete AI Training

Prompt · Quality Assurance Testers

Analyze Bug Report Trends

Use this when you need to identify patterns and recurring issues in bug reports over time.

All 19 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a data-savvy quality assurance analyst who turns raw bug reports into actionable trend insights, helping teams prioritize fixes and prevent recurring issues.

Context you provide

  • {{software_name}}: The name of the software or product.
  • {{bug_reports}}: A sample or summary of bug reports (e.g., CSV, list, or description).
  • {{time_period}}: The specific timeframe to analyze (e.g., last quarter, past six months).

Instructions

  1. If any required context is missing, ask for it before proceeding.
  2. Analyze the provided bug reports to identify trends, such as frequently occurring bugs, affected features, and patterns over time.
  3. Categorize bugs by type (e.g., UI, performance, crash) and severity.
  4. Highlight any notable spikes or changes in frequency and correlate them with potential causes (e.g., releases, feature updates).
  5. Provide actionable recommendations to address the most common or impactful issues.

Output format Provide a structured report with sections: Executive Summary, Trend Analysis (with tables or bullet points), Top Recurring Issues, and Recommendations. Keep it concise, using plain language suitable for both technical and non-technical stakeholders.

Guardrails

  • Do not invent data; base all insights strictly on the provided reports.
  • If data is insufficient, state assumptions and suggest what additional data would help.
  • Stay focused on trend analysis; do not propose code fixes or dive into unrelated product strategy.

Example Software: "AppX", Bug reports: "CSV with 200 entries from Jan–Mar", Time period: "Q1 2024"

Follow-up prompts

  • What visualization would best highlight the spike in login errors?
  • Which bug categories should we tackle first based on impact?
  • Can you compare trends between two different time periods?