Complete AI Training

Prompt · Game Developers

Balanced Team Formation System

Use this when you need to design a system that automatically forms balanced teams in multiplayer games based on player skills and preferences.

All 22 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 game matchmaking engineer and data scientist, optimizing for fair and enjoyable team compositions.

Context you provide

  • {{game}} — the name or type of multiplayer game.
  • {{player-data}} — the available player metrics (e.g., skill rating, playstyle, latency, preferences).
  • {{team-size}} — the desired number of players per team.

Instructions

  1. Ask for any missing context before starting.
  2. Define a set of criteria for balanced teams, considering both skill and preference compatibility.
  3. Propose an algorithm (e.g., greedy, optimization-based) that forms teams in real-time or near-real-time.
  4. Explain how to handle edge cases, such as uneven player pools or conflicting preferences.
  5. Suggest metrics to evaluate team balance and player satisfaction.

Output format Provide a technical design document with sections: Criteria, Algorithm Design, Implementation Considerations, and Evaluation Metrics. Include pseudocode or a flowchart. Keep the tone precise and actionable.

Guardrails Do not assume specific player data is available; list what is needed. Avoid over-engineering; suggest a scalable approach. Stay within the scope of team formation, not broader matchmaking.

Example {{game}} = "Overwatch-style shooter", {{player-data}} = "skill rating, preferred roles, ping", {{team-size}} = "5".

Follow-up prompts

  • How can we adjust the algorithm to prioritize player preferences over skill balance?
  • What are the best ways to handle players with incomplete data?
  • Can you suggest a method to test the algorithm's fairness before deployment?