Getriwaq
Raai is an AI company building NEO, an intelligence ecosystem that monitors building electrical loads to identify devices, predict failures, and optimize energy use. NEO reads the shape of power drawn by each appliance, enabling automated load shifting to solar and off-peak hours while detecting equipment degradation weeks before failure. The system is designed to scale from family villas to hospital plant rooms and factory floors.
- Clean Technology
- Energy
- Internet of Things
- Artificial Intelligence
- Battery Technology
- Data & Analytics
Funding
Founders
Founder details are not available yet.
Product
Problem
Buildings consume electricity inefficiently because their systems operate without awareness of what individual devices are doing or how they are aging. This leads to wasted energy, higher bills, and equipment failures that are discovered only after they become expensive to fix.
Solution
Raai provides an AI ecosystem called NEO that gives buildings intelligence by reading their electrical signatures. NEO identifies every device by the shape of power it draws, so appliance identity travels with the device regardless of where it is plugged in. The system detects performance drift in equipment like compressors weeks before failure, forecasts energy bills, and automatically shifts loads like laundry, water heaters, and car charging onto solar and off-peak hours. NEO also manages battery storage, charging from rooftop solar during the day and discharging in the evening to minimize grid draw. Fault signatures learned in one building are shared across all buildings in the ecosystem, improving detection over time.
Target Audience
Primary customers are Saudi homeowners and real estate developers building residential districts, with planned expansion into hospitals, factories, and other commercial building types.
Features
- Non-intrusive load monitoring that identifies devices by electrical signature rather than socket location
- Predictive maintenance that detects equipment degradation, such as a compressor pulling more power to cool less, weeks before failure
- Automated load shifting that moves energy-intensive tasks to solar generation and low-tariff hours without user intervention
- Battery orchestration that charges from rooftop solar during peak sun and discharges during evening hours to reduce grid dependence
- Cross-building fault learning where signatures of failing sockets or devices discovered in one home are propagated to all connected buildings