WISPAYR / AI ADVISORYStart →
AI/Casework/01 · sentinel-bar-queue
All casework
// CASE / 01 / hospitality

Sentinel — bar-queue & ambient retail watch

Ayr Pavilion (1,500-cap event venue)
hospitalityeventsretail

Edge cameras + small object-detection model giving bar staff a live read on queue length, refusal risk and crowd density.

// Cost
£3.8k hardware + 6 days build. Recurring: ~£0 (no cloud inference).
// Duration
Pilot ran 4 weeks before going steady-state.
// 01 · The problem

Pavilion's bar team had no quantitative signal of queue pressure on busy nights. Decisions on pulling extra staff or opening a second till were made by whoever happened to look up. By the time someone noticed a five-deep queue, walk-aways had already happened.

// 02 · What we did

Deployed cheap PoE cameras above each bar pointed straight down. A small YOLO-class detector runs at the edge counting heads inside fixed polygons. Inference happens on a Mac mini, not in the cloud — no images leave the building. Aggregated counts get pushed every 10s to a dashboard the head bartender keeps on a tablet, with a Dispatch alert when the threshold trips.

// 03 · What the AI did

Object detection + occupancy estimation. Nothing fancier — no tracking, no faces, no behavioural inference.

// 04 · What humans did

Defined the trigger thresholds, designed the operational response, trained staff on what the alerts mean, and stayed the decision-maker on staffing.

// 05 · The outcome

Bar refusals dropped sharply on the busiest 6 nights of pilot. Just as importantly, the head bartender stopped having to physically walk the floor to assess pressure.

// 06 · What broke

First model was trained on stock pedestrian data and missed people sitting on stools as 'in queue'. Re-labelling 400 frames from the venue itself fixed it in a day. Lesson: site-specific data trumps bigger general models.

// 07 · What works

Keep the AI doing one narrow thing it's verifiably good at, and route the decision to a human who already had authority. The dashboard isn't an autopilot — it's a better window.

// 08 · Reusable lessons
  1. 01Edge inference removes the GDPR/privacy conversation almost entirely — no images leave the premises.
  2. 02Don't try to cover every camera angle on day one; one well-placed camera per decision point is plenty.
  3. 03If the AI replaces a judgement call, its alert needs to land where the decision-maker already looks.