RF first.
Camera on trigger.
172.8 GB/day → 128 KB/day. The thesis is not that cameras go away — only that they should run less often. Wi-Fi senses continuously. Vision verifies selectively. Language explains the result.
Wi-Fi senses continuously. The camera wakes only when the radio says something interesting happened.
The radio runs flat-out at sub-2 watts. The camera sits at 5% duty cycle, asleep until a CSI anomaly elbows it. That split — boring continuous sensing, sparse expensive recording — is what gets the daily data volume down from 172.8 GB to 128 KB. Same coverage. Different architecture.
The gap is not subtle. It is architectural.
All four come from the same architectural choice: sense with the radio you already have; record with the camera only when the radio says something matters.
Signal · World-model · Interface.
See the camera-on-trigger loop run on a synthetic site — Open the sandbox.
Signal — continuous + sparse
WiFi CSI runs 24/7 on $4 ESP32-S3 nodes. Cameras stay asleep ~95% of the time and only wake on an RF trigger. Cameras now have a 5% duty cycle.
World-model — latent, not raw
Events are state changes, not frames. The world model is a low-cardinality stream of structured events that fits in any tool, any prompt, any database.
Interface — chat with space
Operators query in natural language. The LLM operates against deterministic events with rollback-safe actions. Co-pilot, not black box.
Continuous video is a streaming problem. Structured events are a telemetry problem.
Where CameraPlus wins.
SA · ID · MY · AE · AU. Each vertical led with the line that lands first, plus the number that closes the argument.
Warehouse / Hangar
"Your lights cost more than your monitoring."
91.5% lighting reduction. Zone-triggered high-bays. Storage zones unlit until a forklift enters.
Cut lighting — light only what’s used → Vertical 2Data Center
"Independent monitoring outside your network path."
Out-of-band awareness via ESP-NOW + LoRa. If the network is down, you still know what's happening in the room.
Cage occupancy, intrusion & SOC 2 evidence → Vertical 3Oil & Gas
"10 days battery, not 10 hours."
200–314 hours autonomy on 500 Wh. Satellite blackout? LoRa sub-GHz fallback says you're alive.
200–314h battery · LoRa out-of-band → Vertical 4Telco Infrastructure
"Equipment drift detection at unmanned sites."
1.59W per site. CSI catches enclosure changes, fan failures, presence at remote BTS, BBU, or shelter sites.
Drift detection at unmanned sites → Vertical 5Manufacturing
"Zone-triggered everything."
Lighting, HVAC, and camera orchestration tied to actual occupancy. The factory dims and warms itself around the workers.
Zone-triggered energy & safety → Vertical 6General Industrial
"Boring-reliable and intelligent in the same box."
RPA rules run 95% of the time, fully auditable. Agentic LLM activates only when something doesn't fit.
RPA floor, agentic ceiling →The moat is physics, not features.
Survive jamming
Jamming makes us sharper. Under WiFi jamming, ESP32 nodes retry more aggressively → more emissions → more CSI samples. When WiFi is fully blocked, we read the physical layer over USB serial straight to a laptop.
A jammer cannot touch copper.
Reason about what it sees
172.8 GB/day of video does not fit in an LLM context. 128 KB/day of structured events does. The world model is the prompt.
Camera-first edge AI can run a classifier. It cannot run a conversation.
Boring-reliable AND intelligent
Deterministic RPA rules cover the 95% case, auditable end-to-end. Agentic LLM activates only on the 5% that doesn't match a rule.
Floor is robust automation. Ceiling is autonomous reasoning. You never get one without the guardrails of the other.
LoRa is the second mouth, not a backup mesh.
CameraPlus carries a Semtech SX1262 sub-GHz radio. It's deliberately on a different frequency band from your WiFi, so a jammer or congestion event on 2.4/5 GHz cannot silence it.
We promise a second independent delivery channel. We do not promise guaranteed multi-hop mesh routing. For an oil rig that loses satellite, one LoRa path to anywhere is the difference between ten hours of silence and an immediate alert.
Even if everything else fails, CameraPlus still talks.
A one-week side-by-side reads like a sentencing.
| Metric (per node, 24/7, one week) | Camera-first edge AI | CameraPlus | Δ |
|---|---|---|---|
| Power draw (continuous) | 23–41W | 1.59W | ~93% lower |
| Data emitted per day | 172.8 GB | 128 KB | ~1,350,000× less |
| Battery autonomy on 500 Wh | 12–22 hours | 200–314 hours | ~14× longer |
| Survives WiFi jamming | Goes blind | Gets sharper | Inverted |
| Out-of-band escape | Network only | LoRa sub-GHz | +1 channel |
| Fits in an LLM context | No | Yes | Architecturally |
Camera baseline: UniFi G5 Bullet, AWS surveillance reference, 4 Mbps. CameraPlus: 3× ESP32-S3 (0.29W each) + 1× gateway (0.37W) + Jetson Orin Nano at 5% duty cycle.
CameraPlus is not for every workload. That's intentional.
CameraPlus is not the right architecture if you need…
- Forensic-grade continuous video evidence
- Identity-grade face or license-plate recognition
- Compliance recording in regulated jurisdictions where video is the legal artifact
- Sub-centimetre localisation
Use cameras for those. We don't fight cameras where they win.
CameraPlus is the right architecture if you want…
- Continuous coverage with sane power and bandwidth
- Independent monitoring that survives network outages
- Conversational query against your physical site
- Energy-orchestration economics that justify the deployment
- A monitoring stack a jammer cannot silence
Deploy a pilot, or run a demonstration.
MonitorPlus →
The hardware is owned and operated for you; you get a monthly report. Four deployment configurations: Edge, Edge + Vision, Resilient Edge, Partner.
See the configurations ShowGuru · a conceptHow a demo should work →
A concept for showing sensing instead of selling it — let the room surface its own data, live, with nobody narrating over it. Seven scenarios, one arc.
Read the concept