case study

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, generating detailed player- and team-level feedback in structured formats — compressing hours of manual video review into fast, repeatable insight.

Industry

Professional Sports – Rugby Union

Client 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. This limits how much footage can realistically be reviewed and slows the feedback loop to athletes.

Case Study Overview

We built an AI application that digitally analyses videos of rugby matches — both competitive fixtures and training sessions — to produce detailed, accurate feedback at team and individual level. The AI recognises teams and players, monitors specific passages of play such as line-outs, and delivers structured analysis that coaches can act on immediately.

the problem

Problem Statement

Manual video analysis is a bottleneck in elite rugby performance coaching. Labour-intensive clip cutting, subjective interpretation, and limited throughput mean coaches often work with a partial picture of what happened on the pitch — and athletes wait longer than they should for actionable feedback.

outcome

Results We Delivered

An overview of the outcomes we delivered

Insight delivery moved from hours of manual video review to fast, structured output that coaches and players can consume in-session. The depth and consistency of analysis improved markedly, opposition review became practical at scale, and the team now has a repeatable framework for integrating performance data across disciplines.

approach

Our Approach

An overview of the approach we took to deliver the results

We worked with the team's coaches and analysts to identify the highest-value in-game scenarios and 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.

application

What We Did

The specifics over what we performed and how we delivered the results

Scenario-specific analysis

Targets the in-game scenarios that matter most — line-outs, set pieces, defensive phases — rather than 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 coaches can integrate into existing game-review workflows.

Opposition review at scale

Opposition footage can be reviewed with the same depth as own-team analysis, giving the team a genuine preparation edge.

Cross-domain data integration

Pitch behaviours can be cross-matched with fitness, dietary and other performance data to build a holistic view of individual and team form.

Coach-ready insight

Output is designed for coaches and analysts — clear, defensible, and ready to drop into team meetings and one-to-one coaching sessions.