
4
4
South Africa
8+ years of experience
I am a South African software builder and incoming MSc Financial Engineering student, focused on AI-assisted enterprise systems, financial technology, and operational decision-support platforms. My current work includes Culltron SmartPort AI Agent for port logistics and AquaGrid Nexus for water-energy resilience. I work mainly with C#, ASP.NET Core MVC, Python, databases, dashboards, automation, and AI-assisted development workflows. I am building practical AI systems that help organizations make better decisions, improve efficiency, and solve real infrastructure and sustainability problems.

Smart Port AI Copilot is an intelligent operations system designed for modern port environments. It acts as a domain-specific AI assistant that helps port operators understand congestion, truck flow, emissions impact, and operational inefficiencies in real time. Unlike generic chatbots, Smart Port is scoped specifically for port logistics. It responds with structured, operational reasoning and focuses only on relevant port data and scenarios. The system can generate executive summaries, suggest operational actions, and simulate decision-making scenarios for improved throughput and reduced delays. The platform demonstrates how AI agents can be constrained to real-world industrial domains, making them safer, more reliable, and more useful in mission-critical environments like logistics infrastructure. Smart Port represents a step toward AI-driven ports that are faster, cleaner, and more efficient.
19 May 2026

Culltron CivicOps AI is an app-first civic operations platform powered by a workflow-specific AI agent. Residents can report issues through the Citizen App, describe a problem in natural language, track reference numbers, follow local areas, receive alerts, and use Copilot for guidance. The AI agent helps transform messy resident reports into structured municipal cases. It can extract the issue, correct area names, classify the category, suggest the relevant department, assign priority, draft citizen responses, recommend area alerts, and produce operational summaries for municipal teams. Municipal users get a command-centre dashboard with department queues, incident action panels, public updates, audit history, and human-in-the-loop decision support. CivicOps does not replace emergency services; it helps structure, route, escalate, and track civic reports so communities and public-sector teams can respond more clearly.
19 May 2026

Culltron CivicOps AI is an app-first civic incident intake and municipal operations platform built for real communities and public-sector workflows. Residents can use the CivicOps Citizen App to report issues, track tickets, follow local areas, receive alerts, and ask Copilot for help. The platform turns messy civic reports into structured cases with reference numbers, category detection, location cleanup, priority scoring, and routing to the correct department. Municipal teams get a command-centre dashboard with department queues, incident action panels, public updates, audit history, and AI-assisted decision support. CivicOps does not replace emergency services; it helps structure, route, escalate, and track civic reports more clearly. IBM Bob was used to accelerate planning, build structure, documentation, and feature development during the hackathon sprint. Final polish, deployment, Android APK packaging, and submission readiness were completed afterward.
17 May 2026

Culltron Smart Port Flow is a live AI-assisted decision-support platform for cleaner, smarter port logistics, built for the AMD Developer Hackathon. Ports and terminals face pressure from truck congestion, berth delays, yard bottlenecks, rising fuel costs, idling emissions, and operational disruptions. This system gives operators a command centre where they can monitor port flow, review incidents, simulate operational scenarios, and receive explainable AI recommendations. The platform includes an operations dashboard, Smart Port AI Agent, Copilot-style operational assistant, scenario simulator, emissions and idling impact views, and recommendation workflows. Instead of only displaying data, the system helps teams understand what actions could reduce congestion, improve throughput, and lower CO₂ impact. The live application is deployed on DigitalOcean, with a Hugging Face Space used as the official project landing page. AMD Developer Cloud credits are available through DigitalOcean for future scaling of heavier AI simulation, forecasting, optimization, and inference workloads. This demo uses seeded/synthetic operational data and does not expose real port, customer, or production data.
10 May 2026