PlayLens
Current sports analysis is passive.
Core trick
Maps a paused 2D play onto a tactical pitch, then has Gemini predict outcomes for player positions the user drags.
Description
Current sports analysis is passive. Coaches watch video and say, "You should have moved left."
PlayLens turns a 2D video recording of a play into an interactive, counterfactual simulation.
PlayLens provides a detailed analysis of the game geared towards various levels of Fans - beginners, new fans and hardcore fans. The explanation is adjusted as per their understanding level of the game.
It also allows a coach to pause a live game feed, "pop" the video into a 2D/3D tactical map, drag a player to a new position (e.g., "What if the defender was two steps closer?"), and use Gemini to simulate and predict the new outcome of the play based on possible outcomes and runs a simulation with a probable outcome of goal vs no goal.
README excerpt
<div align="center"> <img width="1200" height="475" alt="GHBanner" src="https://github.com/user-attachments/assets/0aa67016-6eaf-458a-adb2-6e31a0763ed6" /> </div> # Run and deploy your AI Studio app This contains everything you need to run your app locally. View your app in AI Studio: https://ai.studio/apps/drive/1TikEEwy-wCSkoYhPBgaIcU6ntKcTpQhT ## Run Locally **Prerequisites:** Node.js 1. Install dependencies: `npm install` 2. Set the `GEMINI_API_KEY` in [.env.local](.env.local) to your Gemini API key 3. Run the app: `npm run dev`