Platform Innovation
The connected home,
intelligently managed.
Presciense has developed two platform concepts built on our standards-based IoT agent: an intelligent home platform that unifies broadband, energy, security and family controls in a single operator-led interface; and a connected care extension that brings on-device AI, spatial awareness and life-safety telemetry to assisted living, with no cameras and no cloud dependency.
Intelligent Home Platform
One platform.
Every home service.
Operators already have hardware in every home and a direct relationship with household energy data. Our intelligent home platform is the software layer that turns that position into daily value, unifying connectivity, energy management, security and family controls inside a single operator-led interface built on the residential gateway.
The platform demonstrates what operator-led home services look like in practice: real-time telemetry from the smart meter, Wi-Fi 7 mesh nodes and connected appliances feeding performance management, closed-loop control and household diagnostics, all orchestrated from the device already installed in the home.
Home Dashboard
Household overview with AI-generated insights, family presence detection, energy snapshot and quick controls: everything relevant to the home in a single view.
Connectivity Management
Wi-Fi 7 mesh topology, device-by-device bandwidth allocation, speed diagnostics and proactive fault detection, often before the household notices a problem.
Energy Intelligence
Real-time consumption, solar and battery state, tariff optimisation and direct appliance control. Closed-loop demand flexibility response within operator SLA windows.
Home Security
Sensor status, activity timeline, arm and disarm controls and alert management, all integrated directly into the gateway rather than a separate application.
Family & Parental Controls
Per-person device management, usage insights, content controls and scheduling, giving households meaningful oversight of their connectivity without complexity.
Interactive Platform Demo
See the platform
in action.
Load the Home Hub app inside the device frame to explore how the platform brings connectivity, energy, security and family controls together in a single operator-led interface.
The prototype loads on demand. Every screen connects to a real telemetry pipeline, showing what the production interface looks like.
- Home DashboardAI-generated insights, family presence, energy snapshot and quick controls
- ConnectivityWi-Fi 7 mesh health, per-device bandwidth and proactive fault alerts
- EnergyReal-time consumption, solar/battery flows, tariff optimisation, appliance control
- SecuritySensor status, activity timeline, arm/disarm and alert management
- FamilyPer-person device management, usage insights and content controls
Home Hub Platform
Explore energy, connectivity, security and family controls inside the device frame.
Commercial Value
Why the gateway is the right foundation for home services.
UK broadband providers are positioned on an unrealised opportunity. They already have hardware in every home, relationships with energy suppliers through the smart meter rollout, and the technical capability to integrate security and home automation. What has been missing is the software layer that ties it together and turns that position into daily household value.
For Operators
Engagement that extends beyond connectivity.
Churn reduction through daily household engagement. ARPU uplift via premium service tiers. Referral revenue from energy switching. A value proposition that extends well beyond broadband.
For Households
One interface. Every home service.
Energy costs, connectivity management, home security and family controls in a single place. Multiple services that are genuinely useful together rather than separately.
For the Wider System
Infrastructure that enables flexibility at scale.
A distributed edge layer that enables demand flexibility, richer household data and a practical route to higher-value services, all built on infrastructure already present in every home.
Technical Architecture
Real-time telemetry. Local inference.
Cloud intelligence at scale.
Edge-First Data Pipeline
Every device in a platform deployment is a source of continuous telemetry. The gateway publishes its own hardware metrics: CPU load, memory pressure, thermal state, uptime. Each mesh node publishes signal quality, channel utilisation, connected client counts and per-device throughput. The smart meter publishes consumption, generation, export and tariff state at 10-second intervals. Connected appliances publish operating state and energy draw in real time. All telemetry flows over MQTT to a local broker on the gateway, routing events to the application layer or queuing them for cloud synchronisation at sub-second latency.
Control decisions execute on the gateway without a cloud round-trip. When smart meter data shows solar export peaking and grid tariff prices are low, the platform shifts EV charging load in real time. When a demand flexibility signal arrives from the energy supplier, it responds within the agreed latency window. Because the decision logic runs locally, response time is measured in milliseconds rather than seconds.
On-Device AI & Cloud Intelligence
Local inference is made practical by dedicated NPU silicon from Broadcom, MediaTek, Silicon Labs, Intel and Nvidia. These processors allow quantised models to run continuously at low power alongside the gateway's routing and telemetry functions. Lightweight open-source architectures such as Llama, Mistral or Phi handle pattern recognition and anomaly detection on-device, deployed via LiteRT or ONNX Runtime for efficient NPU execution.
For tasks requiring deeper reasoning or natural language generation, the cloud layer uses model families from OpenAI, Anthropic and Google to process anonymised fleet data, retrain inference models and generate insights that are pushed back to the gateway fleet. The principle is consistent: on-device for anything latency-sensitive or privacy-critical; cloud for anything that benefits from scale and reasoning depth.
Security Model
Security designed into every layer.
Input validation and schema enforcement on all MQTT messages prevent malformed or malicious payloads from reaching the inference stack. Model outputs pass through confidence gating and output filtering before triggering any control action. For any cloud-facing model interaction, prompt injection defences and adversarial robustness testing are part of the deployment pipeline. Model weight updates are cryptographically signed and verified before the gateway accepts them. Household data stays on-device by default; only anonymised, aggregated telemetry leaves for the cloud training pipeline.
Assisted Living Care Extension
Care intelligence built into the connected home.
Our assisted living care extension transforms the operator's existing infrastructure into a care platform. The gateway already provides connectivity and energy intelligence. This layer adds on-device inference, spatial awareness and life-safety telemetry, delivering context, proactive alerts and real-time notification without cameras, without constant cloud dependency, and without compromising household privacy.
Most assisted living technology is built as a standalone product. Our approach starts from the opposite direction: the operator already has the connectivity, the gateway and the relationship with the household. The question our platform answers is whether that infrastructure can carry a care layer. It can.
The care extension runs on the same standards-based modular agent as our energy and home services platform, on NPU silicon from Qualcomm, MediaTek, Broadcom, Intel and Nvidia. It uses the same MQTT telemetry pipeline, the same security model, and the same edge-first architecture. Operators do not need new infrastructure. They need the software layer that puts what they already have to work.
Proof of Concept
Multi-floor home model
Our proof-of-concept demonstrates occupancy context, life-safety telemetry and network awareness operating inside a multi-floor home model, showing how the gateway becomes a care platform without any additional hardware.
Proof-of-concept showing occupancy context, life-safety telemetry and network awareness inside a multi-floor home model.
Supporting Paper
Commercial case for operator-led care
Our commercial paper sets out the full business logic for operator-led smart security, assisted living and healthcare monitoring services , including market sizing, service architecture and deployment models.
Request the paperOn-Device Intelligence
Inference at the edge.
The gateway runs a stack of lightweight inference models on dedicated NPU silicon. These are not threshold monitors or rule engines. They are models trained on population-scale behavioural data in the cloud and deployed as quantised binaries via LiteRT or ONNX Runtime, running continuously on-device and assessing the current state of the home against learned patterns of normal activity.
Sensors and devices publish state changes over MQTT to a local broker on the gateway, where the inference stack processes the incoming event stream in real time. The models draw on motion sequences, door contact timing, temperature gradients and device state simultaneously to build a continuous picture of what is happening and where.
For natural language tasks such as summarising daily activity for a carer or generating plain-language alerts, the cloud layer uses larger model families from OpenAI, Anthropic and Google against anonymised context. On-device for anything latency-sensitive or privacy-critical; cloud for anything that benefits from scale and reasoning depth.
Spatial Awareness
Room-level understanding.
No cameras.
Spatial awareness is derived from the inference stack interpreting a sparse sensor array: motion detectors, door contacts, temperature sensors and the passive sensing capability of the Wi-Fi mesh itself. Room-level occupancy is not read from any single signal. It is inferred from the pattern across all inputs simultaneously, updated in real time as the household moves through the day.
The gateway builds and maintains a live spatial model of the home: which zones are active, which have been quiet, and for how long. That spatial model is the foundation for everything else. Without it, an extended period of inactivity in a single room might be unremarkable. With it, the platform can assess whether that represents a normal rest pattern or something that warrants attention.
The result is genuine context. The inference engine knows it is mid-morning, that the kitchen has been active for twenty minutes, that movement has recently passed from bedroom to bathroom, and that this pattern is consistent with a normal Tuesday. That contextual model is what distinguishes a care platform that understands a household from one that merely watches it.
From Inference to Action
Advice, alerts and intelligent automation.
Alerts are generated when the inference engine reaches a confidence threshold, not when a sensor crosses a hardcoded value. That distinction matters.
A confidence-based alert is informed by the full contextual picture: time of day, recent activity history, deviation from learned norms and the spatial model of the home. The same sensor event that would trigger a false alarm in a naive threshold-based system is assessed in context before anything fires. False positive rates drop significantly. It is the single most important factor in whether care technology actually gets used day to day.
Advice works the same way. Rather than surfacing every anomaly as an alert, the inference engine generates proactive recommendations grounded in what it has learned about the household: a suggestion to adjust a routine, a note that activity patterns have shifted over the past week, a prompt for a welfare check based on accumulated context rather than a single event.
Intelligent automation is the delivery layer. When inference reaches a defined confidence level, MQTT-driven actions execute on the gateway without waiting for a cloud response: a notification dispatched, a contact called, a door unlocked for a first responder, a connected device adjusted. Latency from trigger to action is measured in milliseconds. The cloud is not in the critical path.
Explainability
Why explainability matters in care.
In assisted living, confidence matters as much as detection. Good care technology should not just identify that something has happened. It should help a carer, operator or family member understand why an alert was triggered and how certain that assessment is. Explainable confidence scores reduce false reassurance, improves triage and makes the platform easier to trust over time. That is the difference between technology that gets adopted and technology that gets switched off.
Data Architecture
Structured for care continuity.
High-frequency sensor telemetry flows into a time-series database, the right structure for windowed, pattern-based queries. Significant events and alert triggers are stored in an event store alongside their full inference context, creating a sequential, auditable record for care continuity and review. The cloud training pipeline ingests anonymised, aggregated event data from the deployed fleet, retrains models and pushes updated weights back to every gateway. Individual household data stays on-device throughout.
Commercial Case
A care layer built on infrastructure operators already own.
For Operators
A route into higher-value care services.
Operators can extend into care and safety services grounded in infrastructure they already manage: connectivity, the gateway and the household relationship, without building new platforms from scratch.
For Families
Peace of mind without intrusive monitoring.
Useful, reliable signal rather than constant surveillance. Families get confidence in the wellbeing of those they care for without the privacy compromises of camera-based approaches.
For Health & Care Systems
Earlier intervention. Longer independence.
Earlier detection of declining activity patterns, better prioritisation of care resources, and meaningful support for individuals living independently for longer, at population scale.
Work With Us
Explore what our platform can do for your organisation.
Whether you are an operator, utility, care provider or technology partner, our team is ready to demonstrate both platforms and walk through how they could work for your organisation.