For Property Management, Landlords & Facility Management

Monitoring & Predictive Maintenance
for your buildings

Two products for everyday property management – usable independently of each other. Central equipment monitoring with AI maintenance forecasting and digital protocols.

Property Monitoring

All systems. All buildings. One dashboard.

Heating, PV, elevator, fire alarm, ventilation – regardless of manufacturer. Real-time sensor data, automatic alerts and AI-powered predictive maintenance.

PROPERTIES Sonnenberg Residential Central Business Park Villa Rosenberg South Production Hall SYSTEM MONITORING PELLET HEATING PELLET FILL LEVEL 65% Burn temp. 820°C · 22.4 kW ÖkoFEN · Pellematic Smart XS PV SYSTEM CURRENT OUTPUT 32.6kW String 3: -12% yield SolarEdge · SE15K + P370 VENTILATION VIBRATION 4.8mm/s Motor defect confirmed Helios · KWL EC 500 W Buildings4· 12 systems Maintenance2overdue AI Forecasts2critical Costs (12 mo.)4,850 EUR 61+ manufacturers · 12 categories · Real-time sensor data · 3-channel alerts · AI maintenance forecasting

61+ Manufacturers

SolarEdge, Viessmann, KONE, Siemens, ÖkoFEN, Vaillant, Geze, Fronius, Helios and many more. 6 protocols (REST, Modbus, MQTT, BACnet, ONVIF, KNX).

3-Channel Alerts

Email, push to mobile, phone call for critical conditions. Configurable per building and severity level. With cooldown to prevent alert fatigue.

Auto Reports

Weekly or monthly AI reports by email. Only systems requiring action – no information overload.

12 System Categories

PV, heating, elevator, fire alarm, ventilation, access control, cameras, water, electrical, HVAC, cost management, other.

Real-Time Sensor Data

Temperature, output, vibration, pressure, humidity, fill levels – everything live on the dashboard with history charts.

Multi-Property

Residential, commercial, industrial, private. Manage unlimited buildings and sub-buildings in one account.

Predictive Maintenance & AI

Detect problems before they occur

Predictive maintenance combines IoT sensors with artificial intelligence. Instead of servicing systems on a rigid schedule, the system analyses the actual condition – and warns weeks before a failure occurs.

Internet of Things (IoT) in building technology

Modern heating systems, PV inverters, elevators and ventilation units have digital interfaces (REST API, Modbus, BACnet, MQTT). Tentacl connects to these interfaces and reads operating data in real time – temperatures, output values, vibration patterns, fill levels, operating hours. This data flows hourly into the analytics platform and forms the basis for AI-powered condition assessment.

Temperature

Vibration

Output

Fill levels

Anomaly Detection (Z-Score)

Each sensor value is compared against the rolling average of the last 14–30 days. The Z-score measures how many standard deviations a value is from the mean. From Z > 2.5 a value is classified as an anomaly. The method detects both sudden spikes (burner failure, short circuit) and gradual drifts (declining heating output over weeks).

Remaining Useful Life (RUL)

Remaining Useful Life per ISO 13381-1:2015. Linear regression on the degradation trend of sensor data calculates when a system will reach the critical threshold. Result: a concrete timeframe in days or operating hours until recommended replacement. The ISO standard defines the entire forecasting process – from data collection through feature extraction to confidence calculation.

Failure Probability

A weighted score from four factors: anomaly frequency (30%), degradation trend (30%), system age relative to manufacturer specification (20%) and maintenance history (20%). Result: a failure probability in percent for the next 30 days. From 60% an alert is automatically sent to the property manager.

AI Advisor (Claude AI)

The statistical analysis provides numbers – the AI provides meaning. Claude AI interprets raw data in the context of the respective system type: What does 820°C combustion temperature mean for a pellet boiler? Is 4.2 mm/s vibration normal for a fan motor? Result: plain-language analysis, prioritised action recommendations and cost estimates for each repair.

Practical Example

ÖkoFEN Pellet Boiler – Detecting burner wear early

Starting situation

A residential complex with 3 apartment buildings is centrally supplied via an ÖkoFEN pellet boiler (Pellematic Smart XS). The system has been running for 4,280 operating hours. IoT sensors record hourly: combustion temperature, flue gas temperature, flow temperature, pellet fill level and heat output.

What the AI detects

After 60 days of data collection, Z-score analysis shows: the flue gas temperature is rising gradually by 0.3°C per week – invisible in daily operation, but statistically significant (Z = 2.8). At the same time, heat output is slightly declining. This indicates soot deposits on the heat exchanger.

Forecast

The RUL calculation shows: without cleaning, efficiency will fall below the critical threshold in approx. 45 days. Failure probability: 35% within 30 days, 68% within 60 days. Claude AI recommends: "Have the heat exchanger cleaned, estimated cost 280–400 EUR. If delayed, a burner fault with emergency call-out at the weekend is likely: 1,200–1,800 EUR."

Outcome

The property manager receives an automatic alert by email and push notification. The cleaning is scheduled for the next working day – no emergency, no weekend surcharge, no tenant complaints. Saving: approx. 800–1,400 EUR compared to an unplanned breakdown.

Typical equipment lifespan & maintenance intervals

Pellet Boiler

15–20 yrs.

Maintenance: annual. Burner, heat exchanger, flue gas values. Pellet silo every 3–6 months.

PV Inverter

10–15 yrs.

Degradation 0.3–0.5%/year. String monitoring detects faulty optimisers early.

Elevator

25–30 yrs.

BetrSichV §16 inspection annually. Door motor, cables, brakes. Vibration analysis of guide rails.

Heat Pump

15–20 yrs.

COP monitoring detects efficiency loss. Refrigerant pressure and compressor temperature monitored.

Fire Alarm System

10–15 yrs.

DIN 14675 inspection quarterly. Individual detector age tracked, replacement planned in time.

Ventilation Unit

15–20 yrs.

Vibration sensors on the motor detect bearing wear. CO2 monitoring shows performance decline.

Scientific background

The methods used are based on established standards in condition monitoring: ISO 13381-1:2015 (Condition Monitoring – Prognostics and RUL calculation), ISO 13379-1:2012 (Data interpretation and anomaly detection) and VDI 2888 (Condition-based maintenance). The Z-score method for anomaly detection in IoT time series is peer-reviewed and documented (MDPI Sensors 2024, Nature Scientific Reports 2023).

According to McKinsey & Company (Prediction at Scale, 2024), predictive maintenance reduces maintenance costs by 20–40% and unplanned downtime by up to 50%. Deloitte quantifies the elimination of unexpected failures at 70–75% and the improvement of equipment reliability at 30–50%. Accenture confirms a reduction in maintenance costs of 30%.

Fraunhofer ISE (Freiburg) develops methods for proactive condition assessment of building systems and has analysed over 70,000 photovoltaic modules since 2012 in the TestLab PV Modules. Fraunhofer ITWM (Kaiserslautern) researches mathematical models for condition monitoring and applies machine learning to predictive maintenance in practice. Fraunhofer IPT (Aachen) has developed the vBox – a retrofitting system for vibration monitoring that can also be added to existing systems. Studies by the US Department of Energy demonstrate a tenfold return on investment and 35–45% shorter downtime through prognostic maintenance.

Sources: ISO 13381-1:2015/2025 · ISO 13379-1:2012 · VDI 2888 · McKinsey – Prediction at Scale (2024) · Deloitte – Predictive Maintenance Report · Accenture · Fraunhofer ISE – Photovoltaics Report 2025 · Fraunhofer ITWM – Predictive Maintenance Machine Learning · Fraunhofer IPT – vBox Retrofitting · U.S. Department of Energy · MDPI Sensors (2024) · Nature Scientific Reports (2023)

Digital Protocols

From walkthrough to PDF in 7 steps.

Capture handover protocols, property inspections and inspection reports digitally, sign them and export as PDF. Directly on your smartphone.

Handover Protocol Step 4/7 Room condition Take photo Living room Walls and ceiling In order Flooring Scratch on left Windows and frames Radiator Scratch in laminate, approx. 15cm, left side Next

7-Step Wizard

Master data, rooms, meters, keys, defects, signature, PDF. Ready to use without any training.

Photo Documentation

Photograph room condition, annotate and embed directly into the protocol. With timestamp.

PDF + Email Delivery

Professional PDF generated instantly and sent by email to all parties.

Property Master Data

Rooms, keys, meter readings, contacts centrally stored. Reusable for future protocols.

Templates

Tenant self-disclosure, handover, maintenance report, commercial property. With custom required fields.

Mobile Optimised

On-site capture on smartphone or tablet. Signature directly on the screen.

Target Audiences

For everyone who manages buildings

Property Managers

20–500 properties

Monitor systems, document handovers, fulfil operator responsibilities. Fewer emergency calls, more control.

Landlords

Protect your investment

Avoid heating failures, document handovers with legal certainty. No disputes on move-out.

Caretakers

On-site in the field

Dashboard and protocol on your phone. No paperwork, no 12 different apps.

Return on Investment

Numbers that convince

0
Less downtime (McKinsey)
0
Lower maintenance costs (Deloitte)
0
Fewer unexpected failures
0
Integrated manufacturers

Example calculation: 50 properties

2–3 unplanned heating failures per winter. Emergency at the weekend: 800–2,000 EUR. Avoidable with early warning – saving: 5,000–15,000 EUR/year. Plus: avoided rent reductions, less stress, happier owners.

Compliance

Operator responsibilities fulfilled

Maintenance automatically documented, due inspections notified in good time.

GEFMA 190:2023

Operator responsibility in FM. Automatic documentation.

BetrSichV §16

Elevator inspection. Deadlines monitored, warning when overdue.

DIN 14675

Fire alarm systems. Inspections documented.

TrinkwV §14

Legionella testing. Automatic reminder.

DGUV Regulation 3

Electrical testing. Overdue inspections highlighted in red.

GEG / BImSchV

Energy Act. Heating efficiency monitored.

Try it now

Test both products for free and without obligation.