Building "Captain Cool"
Sarthak Patil developed 'Captain Cool,' a multi-agent AI system designed to act as a virtual IPL captain during a 3-hour hackathon. The system uses Google Gemini's ecosystem to analyze real-time match conditions, including weather, pitch data, and player history. It simulates tactical decision-making through a debate between specialized AI agents, delivering strategic in-game recommendations with reasoning.
- ▪Captain Cool was built during the Agentic Premier League Hackathon using only Google Gemini tools.
- ▪The system features three AI agents: the Head Analyst, the Devil's Advocate, and the Virtual Captain, who debate tactical decisions.
- ▪Real-time data from weather and venue APIs are integrated to inform decisions, such as dew impact and boundary dimensions.
- ▪The application includes a web interface with dual-layer authentication using both Web3 (MetaMask) and Web2 (Firebase) methods.
- ▪Captain Cool outputs not only the recommended action but also the reasoning and the internal agent debate for transparency.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3936031) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Sarthak Patil Posted on May 17 Building "Captain Cool" #ai #webdev #agentaichallenge #automation Building "Captain Cool": A Multi-Agent IPL Strategist Powered by Google Gemini in 3 Hours Cricket is a captain's game. But what if the captain was an autonomous, multi-agent AI "Brain Room" analyzing live weather, pitch soil, and historical matchups in real-time? This weekend, I participated in the Agentic Premier League (APL) Hackathon organized by the incredible team at #gdgcloudpune.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
