Parlay Gorilla — Explainable Sports Analytics Application
Johnny's role: AI product architect—sports-intelligence workflows, explainability requirements, product experience, responsible-use boundaries, data requirements, and AI-assisted delivery coordination.
AI sports analytics and parlay research with transparent confidence scores, multi-selection workflows, and explainable analysis — a research application, not a sportsbook.
Recruiter summary
- What it is
- Explainable sports analytics and parlay research application with confidence communication and responsible boundaries.
- What I directed
- Sports-intelligence workflow design, parlay builder UX, confidence/explainability requirements, responsible-use copy, and AI-assisted delivery coordination.
- What was hard
- Balancing engaging analytics UX with responsible disclaimers and unreliable third-party sports API freshness.
- Evidence
- Portfolio case study and product surfaces in f3ai.dev repo with documented explainability patterns — not independent win-rate verification.
Product problem
Sports analytics users need transparent confidence, explainable picks, and responsible boundaries — not outcome hype or hidden model reasoning.
Product status
Active product surfaces with honest status labels — research/analytics positioning; not a sportsbook or outcome guarantee.
System designed
Consumer sports-intelligence app with data ingestion, analysis pipeline, confidence scoring layer, parlay builder (1–20 legs), and profile modes (Safe/Balanced/Degen).
- →Sports-data ingestion and freshness monitoring
- →Parlay builder with configurable legs (1–20)
- →Confidence and explainability layer on picks
- →Game analysis hub with data-tied narratives
- →Auth, billing, and subscription surfaces
AI-assisted implementation
Coordinated AI-assisted delivery of analysis narratives, confidence UX, and API resilience patterns — with product review on disclaimers and data-freshness handling.
Safeguards and evaluation
- ✓Responsible gambling and decision-support disclaimers
- ✓No win-rate claims without disclosed sample methodology
- ✓Data freshness surfaced where third-party APIs are unreliable
- ✓Research framing — not betting advice or guaranteed outcomes
Verified evidence
- ✓Explainable confidence UX on parlay builder and game analysis surfaces
- ✓Portfolio and product repo documentation of explainability patterns
- ✓Responsible-use copy and mode labels on public surfaces
Known limitations
- •Third-party sports API freshness and coverage gaps
- •No verified long-horizon win-rate or profitability claims
- •Pick confidence is decision support — not a guarantee of outcomes
- •On-chain or performance experiments not presented as live evidence here
Technologies used
Next milestone
Expand confidence UX and data-freshness indicators; document evaluation methodology for any public performance metrics.
Related content
Interested in this kind of product work?
I'm open to roles where AI Product & Automation Systems Specialist skills apply — agentic systems, automation, and evidence-driven product delivery.