Enterprise site intelligence • Powered by Brickelltech
Vigilnt AI connects directly to your existing CCTV cameras and enterprise operational systems on-premise. Detect what matters in real time, automate root-cause analysis, and turn visual signals into proactive safety, compliance, and productivity actions. 100% private — zero footage leaves your site.
of recorded footage is never reviewed. Incidents are found after the fact, if at all, by someone scrubbing a timeline.
per thing you want to catch, in classic video analytics. Every new hazard means a new model, new training data and a new project.
video AI means streaming your floor, your workers and your faces off site. Most factories and regulators will not accept that.
From Operational Signals to Actions You Can Prove
Vigilnt AI converts passive security video into an active, continuous intelligence loop across safety, security, and facility productivity.
No hardware replacement or expensive camera rip-and-replace. Ingests RTSP, ONVIF, and NVR streams across standard industrial networks. Integrates seamlessly with your access control, telemetry, and ticketing stacks.
Define what matters in plain English without labeling thousands of images or waiting months for ML retraining. Vigilnt AI catches subtle anomalies, PPE breaches, forklift near-misses, and bottlenecks in under 3 seconds.
Close the operational loop. Dispatches real-time alerts to wardens, diagnoses root causes, generates audit-ready PDF/HTML evidence packs for OSHA and ISO compliance, and drives continuous site improvements.
Cross-Domain Intelligence
Switch to a tailored, self-explanatory walkthrough designed for your specific vertical. Each dossier features live simulated CCTV feeds, zero-shot regulatory rules, and operational workflows.
Joint Commission • HIPAA
Unassisted patient fall detection, emergency room violence prevention, crash-cart corridor egress, and sterile PPE compliance.
ISPS Code • OSHA 1917
Reach-stacker blind-spot collision prevention, quay-side water immersion hazards, and HazMat container dwell timing.
NFPA 70E • ATEX / IECEx
Flare unlit venting detection, ATEX zone mandatory PPE compliance, remote switchyard lone-worker man-down alerts.
OSHA 1926 • Fatal Four
100% harness tie-off verification on high-elevation scaffolding, crane slewing exclusion zones, and open trench perimeter checks.
NFPA 130 • FTA Transit
Platform yellow-line incursions, live trackbed trespass, escalator pile-up alerts, and aircraft apron ground handling safety.
GLBA • PCI-DSS • Bank Vault
Mandatory two-person dual-custody vault enforcement, cash-in-transit courier escort protection, ATM coercion robbery detection.
ISO 45001 • Sedex / WRAP
Automated buyer audit packs, fire exit polygon obstruction tracking, workstation activity index, carton stack counting.
Municipal • Air-Gapped Safe City
Crowd density and crush risk early warning, street altercation classification, forensic multimodal footage search, multi-camera tracking.
Vigilnt AI sits on top of a perception layer that already runs on your cameras. Tier 1 sees; Tier 2 understands.
Fast perception running next to your cameras and recorders.
A reasoning layer that reads each event the way an experienced supervisor would.
Every camera and recorder feeds in: video, snapshots, and sensor events such as motion, audio exceptions and tampering. Existing cameras, existing recorders.
Each event is read in context: which camera, which area, what that area is watched for, what time it is. The system writes one honest sentence about the scene and decides if it is Normal, Monitor, Alert or Critical.
Alerts go to the right people on the dashboard, mobile app and email, or to on-site sirens and strobes. Everything is indexed so it can be searched, asked about and reported on.
Each item opens the section where you can try it.
This is what an operator sees. Events arrive from the cameras, are read within seconds, and are filed by severity. Only what clears your threshold interrupts anyone.
Every event is counted, classified or not, so these totals match each source’s own view. Line crossings, crowding, anomalies and recorder events sit on one timeline.
How far the reading and search index has caught up with the cameras.
Classic video analytics needs a trained model for every hazard. Vigilnt AI reads each frame as a scene and checks it against incidents written in plain language. Adding one is typing a sentence. It can also answer “nothing is wrong”, which is what keeps false alarms down.
Write what you want watched for, the way you would brief a guard. Pick the kind of camera it applies to and how serious it is.
No retraining. No new model. No downtime.
Write an incident on the left and activate it. You will see how it is added to that camera type and which frames in the sample library it would have caught.
A gate camera should not be asked whether an aisle is blocked. Cameras are grouped by type, and each type has its own incident list and its own yes/no checks. Universal hazards such as fire and a person down are watched everywhere.
The agent answers from your own incident records, counts and footage. It shows its working, cites the frames it used, and says so when it cannot check something. Type, or speak in English, বাংলা, or a mix.
Hello. I can see every camera on site and every incident on record. Pick a question on the right or ask your own.
Every event is indexed by what it looks like and what it means. Describe a scene or a person, or start from a photo, and get ranked matches across every camera in seconds, however large the archive grows.
Know who is on site, spot who should not be, and follow a person across cameras, with privacy controls that decide who sees faces at all.
Each capture is matched against enrolled photos. Matches arrive as side-by-side cards; low-confidence matches are marked for review instead of being trusted.
Faces that match no one are clustered, so one stranger seen nine times is one visitor, not nine alerts.
Select a camera to see when the same person passed it.
No face needed. Describe clothing and colours.
PPE, unattended objects, workstation activity, temperatures and standing safety checks. All from the same cameras, all with evidence attached.
Share of people seen wearing each item, today. Items are described in plain words, so a new item is one more word.
Every person in the frame is checked. Select an item to focus on who is missing it.
Illustrative sample frames, not from a customer site.
A pallet that does not move makes no motion, so motion alarms never see it. Vigilnt AI checks marked areas on a timer and tracks how long each object has been left.
Aisles, fire lanes and secure bays must stay clear. You draw the region, name what to watch for in plain words (“a cart”, “a pallet”, “a person”), and set the rule: alert if an object sits unattended longer than 30 minutes. The clock pauses while someone is working with it and restarts when they leave.
Each watch reports samples per hour, errors, and how long tracks live. “No alerts” is never ambiguous between “nothing was left” and “the camera could not see”.
Activity index per station in 30-minute slots: 0 is the station’s own quiet level, 100 its normal working level. Shift start, break and end show up without any shift calendar.
Maximum temperature per thermal camera, last 24 hours, with the alert line.
Yes/no questions asked on every relevant frame. A check that never fires is reported too, because silence is not proof the floor was clear.
Cartons on a pallet, garment bundles on a table, fabric rolls on a rack: Vigilnt AI counts them from an ordinary camera frame, groups them into stacks, and reports how high each stack is. Pick the object type or click one example in the frame, and it finds the rest. No barcode, no scale, no training.
Who and what came in, how crowded it got, what the recorders heard, and whether every camera is actually working.
Lines count crossings by direction; zones measure occupancy. Drawings scale with resolution, so they survive a camera upgrade.
Bangla and English plates, vehicle type, and whether the plate is on the approved list.
Events from recorders and camera sensors are read the same way as video events.
A camera that has stopped sending is a blind spot. Uptime, last frame and clock drift for every device.
The written work an operations team does every day, done for them: shift handovers, management briefs and buyer-audit evidence, in English or বাংলা, as Word or PDF.
Route by severity and incident type. Each person sets their own threshold.
Every incident links a camera, an area, a type, a time and the things named in its description. The graph connects them so you can ask questions that span cameras: what fires together, what makes an area different, which checks have never fired.
Select a node to see what it connects to.
The same platform, configured in plain language for each kind of site.
Vigilnt AI needs no custom training. It reads each scene on its own and adapts to the place: a home, an estate, a factory, a warehouse, a campus, a street. What you want watched is written in a sentence, not trained into a model, so a new site or a new risk is minutes of work.
Every event is read before anyone is interrupted, and the system can say “nothing is wrong”. Operators see the few that matter.
Ask a question or describe a scene instead of scrubbing hours of recordings across many cameras.
A new hazard or a new kind of site is a sentence, not a project. No training data, no model update, no downtime.
Audit packs, handovers and briefs with dated frames, ready when the buyer or inspector asks.
On-premise and able to run fully air-gapped. Video and faces never leave your network.
Works with the cameras and recorders you have. No rip-and-replace.
A server room appliance, your existing cameras, and a rollout measured in weeks.
Choose between the standard enterprise NVIDIA platform or our certified ECO configuration for 65% lower hardware CAPEX.
Dell PowerEdge T560/R760 or HP ProLiant, NVIDIA GPUs
The standard enterprise deployment. Dual Intel Xeon / AMD EPYC with enterprise-grade NVIDIA GPUs (RTX PRO 5000 / L40S 48GB Ada).
Huawei TaiShan 200 + Atlas 300I Duo (96GB VRAM) / Atlas 800
A high-density ARM64 + Ascend AI NPU platform offering identical software features and zero-shot VLM reasoning at a fraction of the cost.
Compact GPU appliance
For remote gates, small warehouses and sites with weak links. Reports up to a central Vigilnt AI cluster.
One command centre, many plants
Each site keeps its video locally. Only events and descriptions travel, which cuts bandwidth by over 95%.
Indicative sizing. Standard Enterprise runs on Dell/HP with NVIDIA; ECO Appliance runs on Huawei TaiShan/Atlas at ~65% lower CAPEX. Enterprise clusters support up to 200 cameras per node.
Site survey, appliance installed, cameras and recorders connected and grouped.
Incident types and checks written per camera type, with your EHS and security leads.
Alerts reviewed daily; thresholds and wording tuned on your own footage.
More cameras, more sites, more teams. No re-engineering.
A pilot runs on a handful of your cameras, on your premises, for four weeks.
