Revolutionizing Industrial Worker Safety

Accelerating EHS Application Engineering with AI: Renewi’s 2-Day BRD-to-Build Blueprint for Real-Time CCTV-Based PPE & Worker Safety Monitoring

This production use case build demonstrates a full end-to-end, prompt-engineering-driven SDLC in action: an industrial-grade PPE Compliance & Worker Safety Monitoring Platform, architected directly from a Business Requirements Document (BRD) and built on a pre-trained YOLOv8 computer vision model, into a fully functional, stakeholder-ready, cloud-native application in just 48 hours. What typically requires months of human sprint cycles — requirements analysis, AI infrastructure design, backend services, compliance data pipelines, and enterprise frontend dashboards — was executed methodically through structured AI collaboration, with the Principal Solution Architect directing and the AI acting as lead engineer across every layer.

Managing PPE compliance across industrial worksites is one of the most manual, high-risk operational challenges in the EHS sector. Ensuring workers continuously wear required safety equipment — hard hats, high-visibility vests, and other PPE — across multiple zones and CCTV-monitored areas cannot be reliably enforced through human observation alone. Observer fatigue, delayed inspection cycles, absence of photographic evidence, and the impossibility of simultaneous multi-zone monitoring leave organisations exposed to regulatory liability, safety incidents, and audit failures.

Renewi tackled this high-stakes operational problem head-first. The platform delivers always-on AI-driven PPE violation detection, real-time alert generation, restricted zone intrusion monitoring, and executive-grade analytics dashboards — backed by annotated photographic evidence and a full audit trail. The following is the detailed account of how this platform was engineered from BRD to production in 48 hours.

Target

Purpose and Value Proposition

The core mandate for worker safety in regulated industrial environments is strictly defined by regulations including ISO 45001, OSHA 1910, and COSHH in the UK. Manual PPE enforcement workflows are fragile — introducing significant risk during site operations, compliance spot-checks, and incident reporting. Relying on CCTV footage reviewed only after incidents, manual sign-off sheets, and disjointed supervision rosters leaves massive traceability gaps and creates a reactive rather than preventive safety posture.

This platform was engineered to eliminate those gaps. By leveraging a structured AI-driven build process to translate complex operational requirements — specifically derived from the Renewi EHS Lighthouse BRD — into a fully governed, automated detection system, the team delivered a platform that identifies PPE violations in real time, generates evidentiary snapshots at the moment of violation, and maintains a complete audit trail satisfying the traceability standards required by EHS compliance frameworks.

How It Can Be Used

• HSE Directors / EHS Managers: Monitor live violation rates, active alert volumes, and compliance trends across all monitored zones via the executive KPI dashboard. View violation timelines and drill into specific incidents for audit readiness.
• Site Supervisors / Safety Officers: Receive real-time push alerts the moment a PPE violation or restricted zone intrusion is detected. Review annotated photographic evidence directly in the platform and acknowledge alerts with a traceable digital action.
• Platform Architects / Engineering Leads: Access production-ready backend service architecture built on SOLID principles, a clean FastAPI layer with 11 REST and WebSocket endpoints, Supabase PostgreSQL repositories, and Docker Compose deployment topology.
• Quality & Compliance Auditors: Execute full audit readiness by inspecting violation evidence packages, tracing alerts back to originating detection events, verifying SHA-annotated snapshot URLs in Supabase Storage, and reviewing the complete event and alert audit log.
• Executive Stakeholders / Innovation Teams: Open the enterprise React dashboard and experience a fully working, stakeholder-presentation-ready AI safety monitoring platform — from live stream detection through evidence forensics and analytics — without requiring any manual setup.

Value Provided

• Requirement-to-Code Precision: Every high-level EHS requirement — from real-time helmet violation detection to polygon-based restricted zone enforcement — was mapped directly to production FastAPI endpoints, Pydantic validation schemas, Supabase repository methods, and React dashboard components. The rule engine, temporal smoothing logic, and event deduplication mechanism were all implemented in strict alignment with the original BRD specification.
• Sub-2-Second Violation Alert Generation: The YOLOv8 inference pipeline (FR-02) completes single-image detection in under 200ms on CPU and under 50ms on GPU in testing. Combined with the temporal smoothing rule engine enforcing a 1.5-second violation persistence window and the WebSocket push channel to the dashboard, end-to-end alert delivery from violation event to dashboard notification occurs in under 2 seconds.
• Evidence-First Safety Enforcement: Every confirmed violation triggers an annotated snapshot generation pipeline: bounding boxes, class labels, and confidence scores are rendered directly onto the captured frame, uploaded to Supabase Storage, and linked to the event record with a permanent public URL. Audit teams receive photographic evidence for every alert without manual screenshot workflows.
• Zero Model Training Overhead: The platform treats the pre-trained YOLOv8 model (best.pt — trained on 23,000+ industrial images, mAP50 86.6% for helmets, 93.5% for safety vests, 85.3% for gloves) as a production-ready external AI asset. No dataset collection, labeling, fine-tuning, or training infrastructure was required. The full engineering effort was invested in the platform layer around the model.

•        Model Asset & Attribution:The platform utilizes the best.pt model weights from the Workspace Safety Detection repository created by Hafiz Qaim (https://github.com/hafizqaim/Workspace-Safety-Detection-using-YOLOv8).

Licensing & Compliance Note: The core YOLOv8 model architecture and pre-trained weights are governed by the GNU AGPL-3.0 License via Ultralytics. While the surrounding enterprise platform layers (FastAPI backend infrastructure, Supabase data pipelines, and React dashboard) are engineered to a production-ready standard, any commercial production deployment of the underlying model asset must strictly adhere to AGPL open-source copyleft provisions or secure an upstream commercial enterprise license from Ultralytics.

• Complete Audit Trail by Default: Every detection, event, alert, and acknowledgement action is logged in Supabase with UTC timestamps, camera source attribution, and user identity. The event lifecycle — NEW → ACTIVE → ACKNOWLEDGED → RESOLVED — is fully traceable, providing the complete audit evidence required for EHS incident reporting and regulatory inspection.

Technique: The Kavia AI Streamlined Workflow

The technique used to build this platform represents a fundamental shift in how EHS software systems can be engineered. Traditional delivery of a platform of this complexity — encompassing computer vision AI services, real-time streaming architecture, a multi-table cloud database, an enterprise React dashboard, and production Docker deployment — would typically require 4–6 weeks of sprint cycles across specialised engineers.

This delivery compressed that timeline to 48 hours by positioning a structured, prompt-engineering-driven AI collaboration workflow as the primary delivery mechanism. The Principal Solution Architect acted as strategic director, compliance authority, and integration decision-maker — directing the AI through a three-stage build pipeline that sequentially produced every platform layer from architecture documentation through to deployed frontend.

Crucially, the AI did not just “write code.” It acted as the lead architect and planner — ingesting the full BRD, decomposing requirements into functional service boundaries, generating sequence diagrams for complex operations like the RTSP stream inference pipeline and the alert lifecycle state machine, and producing enterprise-grade implementation decisions. This rigorous AI-driven planning phase minimized requirement drift and ensured the YOLOv8 inference singleton pattern, temporal rule engine, and Supabase repository architecture were designed correctly before a single line of implementation code was produced.

Project Timeline and the 2-Day Build

Below is the high-velocity pipeline followed to build the PPE Compliance & Worker Safety Monitoring Platform from BRD to a fully functional, stakeholder-ready application:

1. Requirement Ingestion and Solution Architecture Design

The build began with the AI ingesting the Renewi EHS Lighthouse BRD in full, performing an automated decomposition into user stories, functional requirements, and non-functional requirements. Within the first session, the AI drafted a complete 22-section Solution Architecture Document (SAD) covering Executive Summary, Business Context, Objectives, Scope, Assumptions, Constraints, all Functional and Non-Functional Requirements, End-to-End Architecture, Component Architecture, AI/ML Architecture, Data Flow Architecture, Security Architecture, Integration Architecture, and Deployment Architecture.

It generated detailed Mermaid-syntax architecture diagrams for the full system topology, the AI inference pipeline, the alert lifecycle state machine, and the Supabase integration layer — establishing the complete engineering blueprint before any implementation began. Technology stack decisions were formally documented at this stage with explicit rationale for each choice, ensuring architectural consistency across all subsequent build phases.