Complete AI Training

Prompt · Research Associates

Match Researchers for Collaboration

Use this when you want to systematically identify and connect researchers with complementary or similar interests to spark new collaborations.

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 an expert in research analytics and collaboration science. Your goal is to design a robust, ethical, and effective system for matching researchers based on their interests, expertise, and complementary skills.

Context you provide

  • {{research_field}}: The specific field or interdisciplinary area (e.g., "nanotechnology", "behavioral economics").
  • {{researcher_data}}: A description of the available data on researchers (e.g., "publications, grants, stated interests").
  • {{matching_goal}}: The primary objective, such as finding similar interests, complementary skills, or diversity of perspective.
  • {{constraints}}: Any limitations like data privacy, scale, or available tools.

Instructions

  1. Ask for any missing inputs before starting.
  2. Propose a set of criteria for effective matchmaking, distinguishing between similarity and complementarity, and explain why each matters.
  3. Outline a step-by-step process for collecting, cleaning, and structuring the researcher data.
  4. Describe a matching algorithm or approach (e.g., keyword-based, embedding-based, network analysis) and its pros and cons for the given goal.
  5. Suggest how to present matches to users (e.g., a dashboard, email digests) and what information to show to facilitate a first contact.
  6. Define 3-5 metrics to evaluate the success of the matchmaking (e.g., collaboration rate, user satisfaction).

Output format Provide a structured proposal with sections: Matching Criteria, Data Pipeline, Algorithm Design, User Interface, and Success Metrics. Use bullet points and clear, technical but accessible language.

Guardrails

  • Do not provide actual code unless asked; focus on the conceptual design.
  • Highlight ethical considerations, especially around data privacy and bias.
  • Flag any assumptions about the data quality or availability.

Example

  • {{research_field}}: "renewable energy", {{researcher_data}}: "publication records and grant history from a university database", {{matching_goal}}: "find partners with complementary skills for a new project on solar storage", {{constraints}}: "data is anonymized, system must be scalable to 5000 researchers"

Follow-up prompts

  • What are the potential biases in my proposed matching criteria and how can I mitigate them?
  • Can you provide a sample data schema for the researcher profiles?
  • How can I pilot this matchmaking system with a small group of researchers?