Beyond the Game: Human Performance AI

The description states that Beyond the Game is:

• A human-performance intelligence platform
• That combines:
  • Gameplay and match telemetry
  • Historical player performance
  • Mechanical, tactical and decision-making indicators
  • Machine-learning models
  • Garmin wearable and biometric signals
  • Sleep, stress, activity and recovery information
  • Training workload
  • Self-reported wellbeing and personal context
  • AI-generated explanations and recommendations

It is described as modeling performance using a formula that includes gameplay (G_t), biometric (B_t), recovery (R_t), competitive context (C_t), and historical patterns (H_{t-n:t}).

The system uses GPT-5.6 as an AI reasoning layer to translate technical outputs into understandable narratives, with machine learning models responsible for scoring and pattern detection.

It is not described as a medical diagnostic product but rather as a performance and wellbeing support system.

Evidence Self-reported by the author; no independent verification or data on actual usage or outcomes.

The description states that Beyond the Game:

• Was initially built through a real project delivered to a public university
• Has since moved into a more demanding competitive setting (Spanish first division)
• Is positioned as an AI-native platform unifying gameplay, wearable and wellbeing data
• Aims to explain performance, spot burnout risk, and deliver personalized guidance

It is described as evolving from an internal competition and research environment into a platform capable of supporting players at the highest levels of national competition.

The author frames it as more than just helping people perform better — it's about understanding what affects performance while preserving health, wellbeing and humanity.

Evidence Self-reported; claims are not substantiated with data or external validation.

The description states that the platform supports:

• Players
• Coaches
• Organizations (specifically a university team competing in Spanish first division)

It is implied to be aimed at competitive gamers, particularly those involved in esports or high-performance environments where performance tracking and recovery are critical.

Evidence Self-reported; no explicit segmentation or customer data provided.

Not evidenced. The description does not mention any pricing structure, monetization strategy, or business model.

Evidence No information on how the product would be sold or who pays for it.

The system was built using:

• Game APIs (Riot Games)
• Garmin wearable integrations
• Supabase, Vercel, OVH.com
• CUDA for compute
• GPT-5.6 as reasoning engine
• Codex for code understanding and refactoring

It is described as having a consolidated architecture including:

• Web application for players and coaches
• Backend services for gameplay and wearable data
• Unified player identity and timeline
• Structured human-performance data model
• Machine-learning models for evaluation and pattern detection
• Contextual evidence layer connecting performance, recovery and wellbeing

Codex was instrumental in rebuilding the fragmented codebase from multiple repositories.

Evidence Self-reported; no independent verification of technical implementation or delivery quality.

The description mentions:

• A three-month deployment with 56 players in a university setting
• The university now has an official League of Legends team competing in the Spanish first division
• The project originated from a real client project and was not fictional or experimental

However, there is no mention of revenue, customers, user growth, or product adoption beyond this single university context.

Evidence Self-reported; no external validation or traction metrics provided.

Not evidenced. The description does not compare Beyond the Game to existing platforms in competitive gaming analytics, wearable integration, or performance intelligence tools.

Evidence No competitive analysis or market positioning information.

• Solo development: Only one team member (Aitor Mier) is involved, which raises concerns about scalability and long-term maintenance.
• Unverified claims: The platform’s effectiveness, accuracy of predictions, and real-world impact are not substantiated.
• Privacy risks: Handling sensitive biometric and wellbeing data without clear governance or compliance details.
• Fragmented history: Years of development were spread across multiple systems with undocumented logic, increasing risk of technical debt.
• Lack of commercial traction: No evidence of paying customers, revenue, or market validation beyond a university project.
• AI dependency: Heavy reliance on GPT-5.6 and Codex suggests potential limitations in control and reproducibility.

Evidence Self-reported; no independent confirmation of these risks.

1. What specific performance insights or recommendations have emerged from the university project?
2. How is data privacy managed, especially with sensitive biometric and wellbeing information?
3. Are there any existing partnerships or pilot programs beyond the university?
4. What is the roadmap for monetization and scaling beyond a single-use case?
5. How does the platform handle uncertainty in its AI-generated explanations?
6. Can you provide examples of how the system has influenced coaching decisions or player behavior?
7. What are the key assumptions behind the performance model, and how were they validated?

Evidence These questions are based on the self-reported description and aim to probe unverified claims.