Real-time Analytics
World Rugby wanted to make the Women’s Rugby World Cup 2025 more engaging by unlocking and activating complex match data in real time so broadcasters, commentators, and digital channels could give fans richer insights and better storytelling during matches.
Reported impact
The platform helped World Rugby deliver a more engaging broadcast and digital fan experience with real-time AI-generated commentary insights during the Women’s Rugby World Cup 2025, and it was later extended to other rugby competitions and additional languages.
World Rugby, Capgemini, Stats Perform, and AWS built TryZone IQ as a generative AI platform for live rugby insight generation. The implementation ingests historical and live Opta match data delivered in real time by Stats Perform, then routes that data into generative AI models hosted on Amazon Bedrock to produce short, match-ready narratives about player impact, team trends, and standout performances. TryZone IQ acts as the orchestration and delivery layer, packaging those model outputs for editorial use. Before distribution, analysts review and approve the generated insights to maintain quality and relevance. Approved insights are then pushed into the live broadcast production workflow for commentators and on-screen graphics, and also published to World Rugby’s online and in-app Match Center plus social channels. The source does not name a separate storage service, so storage is not attributed beyond the historical and live data inputs.
Historical and live Opta match data is delivered in real time by Stats Perform into TryZone IQ, where generative AI models hosted on Amazon Bedrock create summaries of player impact, team trends, and standout performances. Analysts review and approve the outputs, which are then fed into live broadcast production, World Rugby’s Match Center, in-app digital experiences, and social media clips.
"Capgemini worked with Stats Perform, Amazon Web Services (AWS), and World Rugby to develop TryZone IQ, an award-winning Generative AI-driven platform that creates insights in real time for use in broadcasts and commentary"
"Of the 1,521 total insights generated, 439 were promoted via World Rugby Match Center, 36 appeared on BBC match broadcasts, and another 32 were used on Instagram posts."
"The outputs are reviewed and approved by analysts to ensure quality and relevance."
"The platform processes historical and live Opta match data delivered in real time by Stats Perform and leverages generative AI models hosted on Amazon Bedrock to create insights"
"Then, the insights are delivered through the live broadcast production workflow for use by commentators and appearing as on-screen broadcast graphics, as well live insight streams on digital platforms and clips on social media."
"TryZone IQ played a key role in what was the most successful and watched Women’s Rugby World Cup in history; generating 1,521 insights that were used across 147 million viewing hours"
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
LinkedIn's Organization JSON-LD lists numberOfEmployees value 846 and sameAs "http://www.worldrugby.org".
Related
AWS Sample Apr 4, 2024 Instituto de Ingeniería del Conocimiento For nearly 20 years, Instituto de Ingenieria del Conocimiento (IIC) has provided renewable energy prediction services to its clients. The research and development center specializes in artificial intelligence (AI) and… 20 million AWS Glue · AWS Lambda · AWS Step Functions 
Anthropic Sample Archived · Oct 4, 2026 International Rescue Committee IRC teams needed to analyze frontline health data quickly enough to influence staffing, outreach, and supplies, but the information came from ministry-run facilities in inconsistent paper and Excel formats and often had… 4+ hours per month saved by half of surveyed pilot users Claude Enterprise Anthropic Sample Archived · Sep 28, 2026 International Rescue Committee IRC wanted proof that AI could turn inconsistent frontline health data into useful local decision support despite electricity constraints, poor connectivity, and ministry-defined indicators that varied across facilities. 2,700+ health facilities across 40 countries Claude Enterprise 