COMMERCIAL E-COMMERCE
Pirladent
A complete commerce experience for dental professionals.
MOHAMAD JARAD · SOFTWARE ENGINEER
Complex systems.
Clear outcomes.
I connect applied AI, real-world data, and thoughtful software engineering to build products that work beyond the demo.
APPLIED AIINDUSTRIAL IOTFULL-STACK DELIVERY
THE WAY I THINK
01
UNDERSTAND THE SIGNALReal-world complexity
Devices · data · people
02
DESIGN THE SYSTEMApplied intelligence
Models · agents · integrations
03
DELIVER THE EXPERIENCESoftware that works
Interfaces · APIs · operations
Architecture → implementation → delivery
01 / SELECTED WORK
Built with purpose.
Engineered end to end.
A selection of commercial products, applied AI systems, and industrial platforms. Different domains. The same care for what happens after shipping.
APPLIED AI · INDUSTRIAL SYSTEMS
AVAROS
Manufacturing intelligence, one conversation away.
ENERGY INTELLIGENCE
HumanEnerDIA
Making industrial energy data useful to people.
AI PRODUCT · MOBILE
Fin Co-Pilot
From a receipt to a clearer financial picture.
02 / THE PRACTICE
The whole system.
Not just the model.
Useful AI is an engineering discipline. It needs reliable data, deliberate boundaries, a good interface, and a path to production.
More about my approach01
Applied AI & agentic systems
Grounded retrieval, workflow orchestration, evaluation, and human approval where it matters.
RAG / LangGraph / LLM integration02
Industrial intelligence & IoT
Connecting physical devices, time-series data, and operator-facing tools into a coherent system.
ESP32 / MQTT / TimescaleDB / Grafana03
Full-stack product delivery
From API contracts and authentication to interfaces, integrations, deployment, and maintainability.
React / Next.js / FastAPI / Flutter / WooCommerce03 / FIELD NOTES
Thinking through
the hard parts.
0102
AI / Agents
Designing AI Systems That Know When to Ask for Approval
Human approval is not a weakness in agentic systems. It is the control layer that makes AI useful for high-stakes workflows.
AI / IoT
Why IoT App Discovery Needs More Than Vector Search
Lessons from building HEDGE ExpertAI: vector search is powerful, but domain discovery improves when semantic retrieval, keyword scoring, and ontology signals work together.