Game-Changing Video Analytics for an International Rugby Union Team
An AI application that digitally analyses competitive and training match videos for an international rugby union team, producing detailed player- and team-level feedback in structured formats and compressing hours of manual video review into fast, repeatable insight.
Company Overview
The client is a professional international rugby union team. Match analysis is a critical part of modern performance coaching, but the work is extremely labour-intensive: analysts watch full games, identify relevant passages of play, cut video clips, and manually compile feedback packs for coaches and players.
That effort limits how much footage can realistically be reviewed and slows the feedback loop to athletes, so coaches often work with a partial picture of what happened on the pitch.
Problem Statement
Manual video analysis is a bottleneck in elite rugby performance coaching. Labour-intensive clip cutting, subjective interpretation and limited throughput mean coaches frequently work from an incomplete view, and athletes wait longer than they should for feedback they can actually act on.
Outcome Delivered
Insight delivery moved from hours of manual review to fast, structured output coaches can use in-session, opposition review became practical at scale, and performance data can now be integrated across disciplines, all without adding headcount to the analysis function.
Executive Overview
The team now gets faster, deeper and more consistent analysis across both its own performance and opposition footage. Coaches can assess specific scenarios, line-outs, set pieces and defensive patterns, without waiting for manual clip cutting, and player behaviours on the pitch can be cross-matched with fitness and dietary data to build a holistic view of form.
Insight delivery moved from hours of manual review to fast, structured output coaches and players can consume in-session, the depth and consistency of analysis improved markedly, opposition review became practical at scale, and the team gained a repeatable framework for integrating performance data across disciplines, all without adding headcount to the analysis function.
Our Approach
We worked with the team's coaches and analysts to identify the highest-value in-game scenarios and to define what good analysis looked like for each. We then trained a model on curated match footage, built the application around coach workflows rather than around the technology, and integrated the output with the team's wider performance-data ecosystem.
The application analyses videos of both competitive fixtures and training sessions to produce detailed, accurate feedback at team and individual level; it recognises teams and players, monitors specific passages of play such as line-outs, and delivers structured analysis coaches can act on immediately.
Challenges
Challenges Faced
Every engagement starts with a clear-eyed view of what was actually getting in the way, because you cannot fix what you cannot see. Here we set out the real constraints the client was working within, the costs and risks they were carrying, and the gaps that needed closing before any meaningful progress could be made.
Let's Transform Your Enterprise Today
Send an EnquiryManual analysis is a bottleneck
Manual video analysis is the bottleneck in elite rugby performance coaching.
Labour-intensive clip cutting
Analysts spend hours cutting clips by hand before any insight reaches a coach.
Subjective interpretation
Interpretation is subjective, so the same footage can yield different conclusions.
Limited throughput
Limited throughput means coaches often work with only a partial picture of the match.
Deployed solutions
What We Did
A look at how we approached the work, from the first discovery sessions through to the changes we put in place, and the thinking behind each decision along the way. The aim is always the same, to deliver something measurable that the client owns and can build on, rather than a one-off fix that fades once we leave.
Scenario-specific analysis
It targets the in-game scenarios that matter most, line-outs, set pieces and defensive phases, rather than producing generic match summaries.
Team and player recognition
The model recognises teams and individual players, enabling both collective and individual feedback from the same footage.
Structured output formats
Analysis is delivered in consistent, structured formats that fit into existing game-review workflows.
Opposition review at scale
Opposition footage can be reviewed with the same depth as own-team analysis, giving a genuine preparation edge.
Cross-domain data integration
Pitch behaviours can be cross-matched with fitness, dietary and other performance data for a holistic view of form.
Coach-ready insight
Output is designed for coaches and analysts, clear and defensible, ready to drop into team meetings and one-to-one sessions.