A national QSR operator managing 300+ outlets was burning energy on fixed schedules and losing brand consistency at scale. BootLabs built an always-on AI system that sees every store, acts on what it finds, and catches compliance issues before customers do.
A national QSR operator managing 300+ outlets faced two persistent, expensive problems. First, energy waste: HVAC systems, lighting, and kitchen equipment ran on fixed schedules regardless of footfall — burning energy in empty stores, during off-hours, and in unused zones. Second, brand compliance: at any given time, some outlets had unlit signage, missing branding elements, malfunctioning logo lights, or incorrect lighting setups — damaging brand consistency and customer experience. Both problems were invisible without someone physically in every store at every hour. The operator needed an always-on system that could see the state of every outlet and act on it automatically. BootLabs built an AI system combining computer vision on in-store cameras with IoT sensor data to continuously monitor store state — automating energy scheduling based on real footfall and flagging brand compliance issues before customers walk through the door.
Lighting, HVAC, and kitchen equipment ran on time-based schedules with no awareness of actual footfall or store state. Stores used full power during off-peak hours and even after closing — across 300+ outlets, this represented a substantial unnecessary energy spend that compounded every single day.
Outlet branding elements — illuminated signage, logo displays, window lighting, menu board illumination — degraded or malfunctioned without the operations team knowing until a customer complained or a field visit caught it. No central visibility existed across the estate, meaning brand failures were discovered after the damage was already done.
Both energy and compliance issues were only discovered after the fact: during manual audits, field visits, or customer feedback. By then, the cost was already incurred and the brand impression was already made. The operations model had no mechanism for prevention — only for reaction.
In-store cameras run person detection and zone occupancy models at the edge. The system continuously estimates live footfall by zone — entrance, dining area, counter, kitchen. This real occupancy signal drives automated HVAC and lighting adjustments. Not a clock on a wall — actual store state, updated in real time.
Smart energy meters, door sensors, and equipment status monitors feed real-time data alongside camera inputs. The AI fuses occupancy data with energy consumption readings to detect anomalies: HVAC running in a clearly empty store, equipment left on after closing, consumption spikes with no corresponding footfall.
A separate CV model runs on cameras pointed at branding elements — exterior signage, illuminated logo displays, window lighting. The model detects whether each element is illuminated, present, and correctly configured against a reference standard for that outlet type — checking before opening, during trading hours, and after close.
Energy adjustments — dimming, HVAC setback, equipment standby — are triggered automatically based on occupancy signals within policy guardrails set by the operator. Brand compliance failures trigger real-time alerts to the outlet manager and regional operations team with camera evidence, before the trading day begins if caught during pre-open checks.
The system deployed progressively across the outlet estate with edge inference running on existing camera infrastructure. Energy savings began accumulating from day one of operation — no fixed schedules, no wasted load in empty stores. Brand compliance scores lifted from approximately 70% at baseline to 95% within the first operational quarter, driven by pre-open checks that caught failures before customers arrived. ROI was achieved within the first operational year.
Significant reduction in annual energy spend with ROI achieved within the first operational year. Energy is now consumed in proportion to actual store activity, not fixed schedules that assume every hour is the same.
Franchise operators receive daily compliance scores and can address issues before customer impact. Brand standards that were previously invisible at scale are now continuously measured and enforced — without field visits.
The operations team moved from reactive site visits to data-driven targeted interventions at underperforming outlets. Time and resource is now directed at the stores that actually need attention — not spread evenly across the estate.
Real energy consumption data by outlet enables accurate carbon footprint tracking and sustainability reporting. The operator now has an auditable, outlet-level energy dataset that supports ESG disclosures — not estimates from spreadsheets.
Tell us about your challenge and we'll set up a focused 30-minute session.