Research Prompt Library
Accelerate your research process with AI-powered prompts for academic papers, market analysis, competitive research, and data interpretation. Generate hypotheses, structure methodologies, and analyze findings efficiently.
63 Research Prompts Available
All
63
Academic
18
Market Research
15
Competitive
12
Data Analysis
10
Literature Review
8
Academic • Literature Review
Literature Review Structure
Create a comprehensive literature review structure for a research paper on [Topic]. Include sections for introduction, theoretical framework, methodology review, key findings synthesis, research gaps, and conclusion.
Mixed Methods
Literature Review on "AI Ethics in Healthcare"
1. Introduction
• Overview of AI adoption in healthcare
• Importance of ethical considerations
• Research objectives and scope
2. Theoretical Framework
• Ethical theories (utilitarianism, deontology, virtue ethics)
• AI ethics principles (transparency, fairness, accountability)
• Healthcare ethics principles (beneficence, non-maleficence)
3. Methodological Review
• Analysis of 45 peer-reviewed articles (2018-2023)
• Mixed-methods approach: content analysis + case studies
• Inclusion/exclusion criteria defined
1. Introduction
• Overview of AI adoption in healthcare
• Importance of ethical considerations
• Research objectives and scope
2. Theoretical Framework
• Ethical theories (utilitarianism, deontology, virtue ethics)
• AI ethics principles (transparency, fairness, accountability)
• Healthcare ethics principles (beneficence, non-maleficence)
3. Methodological Review
• Analysis of 45 peer-reviewed articles (2018-2023)
• Mixed-methods approach: content analysis + case studies
• Inclusion/exclusion criteria defined
Review Structure:
Introduction & Background
Theoretical Framework
Methodological Review
Key Findings Synthesis
Research Gaps & Future Directions
Example Input:
Topic: AI Ethics in Healthcare Applications
Time Frame: 2018-2023 publications
Scope: Clinical decision support, diagnostics, patient monitoring
Market Research
Market Analysis Framework
Develop a comprehensive market analysis for [Product/Service] targeting [Target Market]. Include market size estimation, growth projections, competitive landscape, customer segmentation, and SWOT analysis.
Quantitative
Market Analysis: AI-Powered Writing Assistant for Enterprises
1. Market Size & Growth
• Total Addressable Market (TAM): $4.2B (2023)
• Serviceable Addressable Market (SAM): $1.8B
• CAGR: 24.3% (2023-2028)
• Key drivers: Remote work, content marketing growth, AI adoption
2. Competitive Landscape
• Direct competitors: Grammarly Business, Jasper, Copy.ai
• Indirect competitors: Microsoft Editor, Google Docs AI features
• Market share analysis: Top 3 players control 58% of enterprise segment
3. Customer Segmentation
• Enterprise (500+ employees): 42% of market
• Mid-market (100-499 employees): 31%
• SMB (1-99 employees): 27%
1. Market Size & Growth
• Total Addressable Market (TAM): $4.2B (2023)
• Serviceable Addressable Market (SAM): $1.8B
• CAGR: 24.3% (2023-2028)
• Key drivers: Remote work, content marketing growth, AI adoption
2. Competitive Landscape
• Direct competitors: Grammarly Business, Jasper, Copy.ai
• Indirect competitors: Microsoft Editor, Google Docs AI features
• Market share analysis: Top 3 players control 58% of enterprise segment
3. Customer Segmentation
• Enterprise (500+ employees): 42% of market
• Mid-market (100-499 employees): 31%
• SMB (1-99 employees): 27%
Analysis Framework:
Market Size & Growth Projections
Competitive Analysis (Porter's Five Forces)
Customer Segmentation & Personas
SWOT Analysis
Market Entry Recommendations
Example Input:
Product: AI-Powered Writing Assistant for Enterprises
Target Market: Mid-to-large enterprises (100+ employees)
Geography: North America & Europe initially
Competitive Analysis
Competitor SWOT Analysis
Conduct a detailed SWOT analysis for [Competitor Name] in the [Industry] sector. Analyze their strengths, weaknesses, opportunities, and threats based on recent performance, product offerings, and market position.
Qualitative
SWOT Analysis: OpenAI (AI Platform Market)
Strengths
• Pioneer in large language models (GPT series)
• Strong brand recognition and credibility
• Extensive developer community and API ecosystem
• Microsoft partnership provides cloud infrastructure and distribution
• Leading research team with continuous innovation
Weaknesses
• High operational costs for model training and inference
• Limited transparency in some model development processes
• Dependency on venture funding (though reduced with Microsoft investment)
• Ethical and safety controversies affecting public perception
Strengths
• Pioneer in large language models (GPT series)
• Strong brand recognition and credibility
• Extensive developer community and API ecosystem
• Microsoft partnership provides cloud infrastructure and distribution
• Leading research team with continuous innovation
Weaknesses
• High operational costs for model training and inference
• Limited transparency in some model development processes
• Dependency on venture funding (though reduced with Microsoft investment)
• Ethical and safety controversies affecting public perception
Analysis Components:
Internal Strengths
Internal Weaknesses
External Opportunities
External Threats
Strategic Implications
Example Input:
Competitor: OpenAI
Industry: AI Platform and LLM Providers
Time Frame: 2023-2024 analysis
Data Analysis • Academic
Research Hypothesis Generation
Generate testable research hypotheses for a study investigating the relationship between [Variable A] and [Variable B] in the context of [Research Domain]. Include null and alternative hypotheses with operational definitions.
Quantitative
Research on "AI Adoption and Productivity in Software Development"
Main Research Question:
Does the adoption of AI-assisted coding tools affect developer productivity and code quality in enterprise software teams?
Hypothesis 1 (Productivity)
• H1: Teams using AI coding assistants complete coding tasks 25% faster than teams without such tools
• H0: There is no significant difference in task completion time between teams with and without AI coding assistants
Hypothesis 2 (Code Quality)
• H2: Code written with AI assistance has 30% fewer bugs in initial testing phases
• H0: There is no significant difference in bug rates between code written with and without AI assistance
Operational Definitions
• "Productivity": Lines of functional code delivered per developer hour
• "Code Quality": Number of critical bugs reported in first 30 days post-deployment
Main Research Question:
Does the adoption of AI-assisted coding tools affect developer productivity and code quality in enterprise software teams?
Hypothesis 1 (Productivity)
• H1: Teams using AI coding assistants complete coding tasks 25% faster than teams without such tools
• H0: There is no significant difference in task completion time between teams with and without AI coding assistants
Hypothesis 2 (Code Quality)
• H2: Code written with AI assistance has 30% fewer bugs in initial testing phases
• H0: There is no significant difference in bug rates between code written with and without AI assistance
Operational Definitions
• "Productivity": Lines of functional code delivered per developer hour
• "Code Quality": Number of critical bugs reported in first 30 days post-deployment
Hypothesis Structure:
Research Question Formulation
Alternative Hypothesis (H1, H2...)
Null Hypothesis (H0)
Operational Definitions
Testability Criteria
Example Input:
Variable A: AI Coding Tool Adoption
Variable B: Developer Productivity & Code Quality
Domain: Enterprise Software Development
Academic • Experimental Design
Experimental Methodology Design
Design an experimental methodology to test [Research Question]. Include participant selection criteria, experimental conditions, control variables, measurement instruments, and statistical analysis plan.
Experimental
Experiment: "Effect of AI-Generated Content on Reader Trust"
1. Research Design
• Between-subjects experimental design
• 3 conditions: Human-written, AI-generated, AI-assisted human-written
• Random assignment of 300 participants (100 per condition)
2. Participants
• Recruited via Prolific Academic platform
• Inclusion: English fluency, college education, regular news readers
• Exclusion: Professional writers, AI researchers
• Demographic quotas: Age, gender, education level
3. Experimental Procedure
• Phase 1: Read 3 articles (one per condition, randomized order)
• Phase 2: Complete trust assessment questionnaire (7-point Likert scale)
• Phase 3: Identify which articles they believe were AI-generated
• Debriefing: Full disclosure of article origins
1. Research Design
• Between-subjects experimental design
• 3 conditions: Human-written, AI-generated, AI-assisted human-written
• Random assignment of 300 participants (100 per condition)
2. Participants
• Recruited via Prolific Academic platform
• Inclusion: English fluency, college education, regular news readers
• Exclusion: Professional writers, AI researchers
• Demographic quotas: Age, gender, education level
3. Experimental Procedure
• Phase 1: Read 3 articles (one per condition, randomized order)
• Phase 2: Complete trust assessment questionnaire (7-point Likert scale)
• Phase 3: Identify which articles they believe were AI-generated
• Debriefing: Full disclosure of article origins
Experimental Components:
Participant Selection & Sampling
Experimental Conditions
Procedure & Timeline
Measurement Instruments
Statistical Analysis Plan
Example Input:
Research Question: How does AI-generated content affect reader trust compared to human-written content?
Content Type: News articles on technology topics
Measurement: Trust ratings, credibility assessments
Data Analysis • Interpretation
Research Findings Interpretation
Interpret the following research findings on [Topic] and provide meaningful conclusions, limitations discussion, and recommendations for future research. Connect findings to existing literature and practical implications.
Mixed Methods
Interpretation of AI Diagnostic Tool Study Results
Key Findings:
• AI diagnostic tool achieved 94.2% accuracy vs. 88.7% for human radiologists
• False positive rate: 3.2% (AI) vs. 5.8% (human)
• Processing time: 2.3 minutes (AI) vs. 8.7 minutes (human average)
• User satisfaction: 4.2/5.0 for AI-assisted workflow
Interpretation:
1. The 5.5% accuracy improvement is statistically significant (p < 0.01) and clinically meaningful
2. Reduced false positives suggest AI may help minimize unnecessary follow-up procedures
3. Time savings could increase department throughput by approximately 28%
4. High satisfaction indicates good human-AI collaboration potential
Connection to Literature:
• Consistent with Esteva et al. (2021) showing AI superiority in image classification tasks
• Extends previous work by demonstrating workflow integration feasibility
Key Findings:
• AI diagnostic tool achieved 94.2% accuracy vs. 88.7% for human radiologists
• False positive rate: 3.2% (AI) vs. 5.8% (human)
• Processing time: 2.3 minutes (AI) vs. 8.7 minutes (human average)
• User satisfaction: 4.2/5.0 for AI-assisted workflow
Interpretation:
1. The 5.5% accuracy improvement is statistically significant (p < 0.01) and clinically meaningful
2. Reduced false positives suggest AI may help minimize unnecessary follow-up procedures
3. Time savings could increase department throughput by approximately 28%
4. High satisfaction indicates good human-AI collaboration potential
Connection to Literature:
• Consistent with Esteva et al. (2021) showing AI superiority in image classification tasks
• Extends previous work by demonstrating workflow integration feasibility
Interpretation Framework:
Statistical Significance Assessment
Literature Connection
Limitations Discussion
Practical Implications
Future Research Directions
Example Input:
Topic: AI vs. Human Performance in Medical Diagnostics
Study Type: Comparative clinical trial
Metrics: Accuracy, time, false positives, user satisfaction
AI Research Assistant
Streamline your research workflow with our AI Research Assistant. Generate literature reviews, design methodologies, analyze data, and interpret findings with intelligent research guidance.
Launch Research Assistant