Data Analyzer Simple
---
title: Research Data Analyzer
type: simple
category: productivity
last_updated: 2025-09-05
tested_platforms: ["ChatGPT 4", "Claude 3"]
target_users: ["non-technical", "business users"]
output_format: document
---
# Research Data Analyzer
## What this does:
Analyzes survey results, research data, or study findings to extract key insights, identify patterns, and provide actionable recommendations.
## How to use:
1. Copy this entire prompt
2. Paste your research data or survey results
3. Submit to any AI assistant
4. Get clear insights and recommendations
## The Prompt:
Analyze this research data and provide clear, actionable insights that I can use for decision-making. Format the analysis as a professional report with key findings and practical recommendations.
**Research Data:**
[PASTE YOUR DATA HERE - this could be survey results, study findings, customer feedback, market research, etc.]
**Context Information:**
- Type of research: [WHAT KIND OF STUDY - example: "Customer satisfaction survey"]
- Who was surveyed/studied: [PARTICIPANTS - example: "Current customers who bought in last 6 months"]
- Sample size: [HOW MANY PEOPLE - example: "500 responses"]
- Time period: [WHEN CONDUCTED - example: "December 2023"]
- Purpose: [WHY YOU DID THIS RESEARCH - example: "Improve customer experience"]
**What I Need to Know:**
- Main question: [PRIMARY THING YOU WANT TO UNDERSTAND - example: "What are customers most unhappy about?"]
- Decision to make: [WHAT YOU'LL DO WITH INSIGHTS - example: "Decide which service improvements to prioritize"]
- Success metrics: [HOW YOU MEASURE SUCCESS - example: "Customer retention rate, satisfaction scores"]
Format the analysis as:
**RESEARCH ANALYSIS REPORT**
**Executive Summary:**
- Most important finding
- Key recommendation
- Confidence level in findings
**Key Findings:**
**1. Main Insights:**
- Finding #1: [What the data shows, with specific numbers/percentages]
- Finding #2: [What the data shows, with specific numbers/percentages]
- Finding #3: [What the data shows, with specific numbers/percentages]
**2. Patterns Identified:**
- Demographic trends: [How different groups responded]
- Behavioral patterns: [What behaviors correlate with outcomes]
- Unexpected discoveries: [Surprising findings]
**3. Problem Areas:**
- **Biggest concern:** [Most significant issue found]
- Impact: [How serious this is]
- Evidence: [Data supporting this]
- **Secondary issues:** [Other problems identified]
- Impact: [How serious these are]
- Evidence: [Data supporting these]
**4. Positive Highlights:**
- **Strengths identified:** [What's working well]
- **Opportunities:** [Areas with potential for growth]
- **Success factors:** [What drives positive outcomes]
**Statistical Significance:**
- Reliability of findings: [How confident we can be]
- Sample limitations: [What might affect accuracy]
- Areas needing more research: [What questions remain]
**Actionable Recommendations:**
**Immediate Actions (Next 30 Days):**
1. [Specific action]: [Why this matters, expected impact]
2. [Specific action]: [Why this matters, expected impact]
**Short-term Initiatives (3-6 Months):**
1. [Bigger project]: [Why this matters, expected impact]
2. [Bigger project]: [Why this matters, expected impact]
**Long-term Strategy (6+ Months):**
1. [Strategic change]: [Why this matters, expected impact]
2. [Strategic change]: [Why this matters, expected impact]
**Priority Matrix:**
- **High Impact, Easy to Implement:** [Quick wins]
- **High Impact, Hard to Implement:** [Major projects worth the effort]
- **Low Impact, Easy to Implement:** [Nice-to-haves for slow periods]
- **Low Impact, Hard to Implement:** [Avoid these]
**Success Measurement:**
- How to track progress on recommendations
- Key metrics to monitor
- Timeline for seeing results
**Next Research Needed:**
- Questions this study didn't answer
- Additional data that would be helpful
- Recommended follow-up studies
Make the insights specific and actionable, focusing on practical steps I can take based on what the data reveals.when to use it
Community prompt sourced from the open-source GitHub repo rada-ii/universal-llm-prompts (MIT). A "Data Analyzer Simple" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.
tags
productivitycommunitydeveloper
source
rada-ii/universal-llm-prompts · MIT
more in Productivity
Productivity✓ tested
Summarize a doc into decisions & actions
chief of staff who extracts what to DO, not just what was said
Productivity✓ tested
Draft a reply to a hard email
calm, direct communicator who de-escalates without caving
Productivity✓ tested
Turn a brain-dump into a weekly plan
planning coach who protects your focus, not just your calendar