Cricket, with its intricate strategies and deep history, increasingly captivates a global audience. The Indian Premier League (IPL), a Twenty20 league in cricket, highlights the best of global talent in a fast-paced format lasting just a few hours, unlike the longer formats of the game. Renowned for its fusion of technology and fan engagement, the IPL stands as the world's most popular cricket league. This study concentrates on Dream11, India’s leading fantasy cricket league for IPL, where participants craft virtual teams based on real player performances to compete internationally. Building a winning fantasy team requires navigating various complex factors including player form and match conditions. Traditionally, this has been approached through operations research and machine learning. This research introduces the FanCric framework, an advanced multi-agent system leveraging Large Language Models (LLMs) and an open-source orchestration framework to automate the fantasy team selection in cricket. FanCric thus leverages both structured and unstructured data to generate teams. The benchmark analysis involves scrutinizing approximately 12.7 million unique entries from a Dream11 contest, evaluating FanCric’s efficacy against the collective wisdom of crowds and a simpler prompt engineering approach. We further evaluated the impact of generating varying numbers of teams. The exploratory findings in this study are promising, indicating that further investigation into FanCric’s capabilities is warranted to fully realize its potential in enhancing strategic decision-making using LLM’s in fantasy sports and business in general.