AI + AR measurement for lawn bowls, Bocce, and precision sports.
Built and delivered an AI + AR lawn bowls measurement app using a YOLO-trained computer vision pipeline, native iOS, and LiDAR-assisted measurement, with expansion planned for Bocce and similar precision sports.
Role
Founder, computer vision lead, mobile AR product builder
Timeline
2024 - Present
Users
4K+ players/downloads publicly positioned
98%+
High-accuracy measurement positioning
<3 sec
Fast shot measurement
4K+
Player-scale traction
Built a YOLO-based computer vision training pipeline after annotating sport-specific data.
Developed a native iOS app using LiDAR-supported AR measurement flows on compatible phones.
Designed the product around speed, fairness, accessibility, and reduced disputes during play.
Problem
Close-shot decisions in lawn bowls are still slowed by visual guessing and manual tape measurement, creating friction during play.
Solution
WGTS uses phone-based AI and AR measurement workflows to make shot decisions faster, more objective, and more accessible.
Execution
WGTS uses phone-based AI and AR measurement workflows to make shot decisions faster, more objective, and more accessible.
Bowl and jack detection workflow
AR measurement experience
LiDAR-supported spatial sensing
Native iOS product implementation
3D WebGL game prototype direction
Expansion model for Bocce and similar sports
Technology signals
On-green measurement context
The WGTS public site anchors the product in the real moment of play: close calls on the green where speed and fairness matter.
Source: whosgottheshot.comProject Gallery
These visuals come from the official public-facing project surfaces and help ground the case study in the actual product experience, not just portfolio copy.
Execution Surface
The strongest work sits at the intersection of product judgment, technical architecture, and operating constraints.
Technology Signals
Built a YOLO-based computer vision training pipeline after annotating sport-specific data.
Developed a native iOS app using LiDAR-supported AR measurement flows on compatible phones.
Designed the product around speed, fairness, accessibility, and reduced disputes during play.
Started expansion from lawn bowls into Bocce, WebGL game experiences, and future Unity mobile rollout.
Bowl and jack detection workflow
AR measurement experience
LiDAR-supported spatial sensing
Native iOS product implementation
3D WebGL game prototype direction
Expansion model for Bocce and similar sports
Outcomes
Lessons
Recruiter Takeaway
Mohammed can build applied AI products that combine model work, mobile execution, user experience, and market expansion.
These are public-safe architecture layers: enough to show leadership judgment without exposing sensitive implementation detail.
The iOS app uses camera and AR flows to support quick, phone-based measurement moments.
Object-detection work identifies sport-specific targets before measurement decisions are presented.
The product roadmap extends from utility measurement into 3D WebGL and mobile game experiences.
More Work
LEO AI
AI Platform
Built LEO as a multi-surface AI platform spanning public intake, officer workspace, agency administration, and platform operations, with agentic RAG, cited legal answers, credit governance, answer-quality review, support workflows, and knowledge-base operations.
4
Website, Officer, Agency, and Admin surfaces
6
Controlled AI legal work modes
NexxusOne
Secure SaaS
Built and delivered a secure public-safety collaboration platform for law enforcement agencies, modernizing officer coordination, secure messaging, case workspaces, and encrypted information sharing.
300+
Officer-scale adoption
AES-256
Enterprise-grade encryption posture
TerraGrow
AgriTech
Led TerraGrow as a founder/operator, building agritech data systems that connected AI, IoT, cultivation intelligence, dashboards, and business operations.
$2M
Venture-backed execution
3M+
Large-scale agritech telemetry