← All case studies
Case 01· Manufacturing & Logistics· 2025· Computer Vision

A 16-camera QC system that runs entirely on-premise.

Every pack photographed. Every docket searchable. Every anomaly surfaced — without a single frame leaving the warehouse.

Client
Havit Group
Sector
Wholesale lighting manufacturing
Engagement
Design, build & deploy
Timeline
Phase 1 — MVP delivered
§ 01 The brief

The problem

Havit's packing line runs 16 stations, each producing dockets that get taped to outgoing cartons. When a customer disputed an order, the QC team had two options: trust the paper trail, or spend hours reviewing raw CCTV.

Neither scaled. The existing cameras were only useful after the fact — there was no way to search by docket number, no confidence that anything had actually been captured, and no record tying a pack to the product leaving the door.

The approach

We proposed a local-AI vision system that monitors all 16 stations continuously, captures the best frame of every pack, reads the docket number with OCR, and makes the whole thing searchable in seconds.

Every part runs on hardware in the warehouse. No cloud APIs, no monthly per-seat fees, no data leaving the premises. The system was designed so the QC team could use it immediately and the engineering team could extend it without us.

Measured outcomes.

16
Cameras live
on one box
<5s
Docket number to
full photo record
100%
On-premise
zero cloud calls
0
Ongoing vendor
API fees
§ 02 Approach

Monitoring all the time — storing only what matters.

The cameras already existed. The hard part was making them useful. We built a system that watches every station continuously but only captures and records when a pack actually happens — the moment a docket appears, and the moment it leaves.

Everything runs on a single box inside the warehouse. No cloud subscriptions, no per-camera SaaS fees, no video streams leaving the premises. Sixteen cameras on modest hardware, built so the QC team can use it immediately and Havit's own engineers can extend it without us in the loop.

§ 03 Inside the system

Two tools, built for different jobs.

Operations

The health view

A dashboard for the warehouse manager: sixteen cameras at a glance, each one green, amber or red. Live alerts the moment anything stops working. Sensitivity can be tuned per station without touching code or calling us.

QC team

The daily tool

Type a docket number, get the photo record in under five seconds. The full event timeline — when the docket arrived, when packing finished, when the carton left — with confidence-scored photos for every stage. No training, no manual.

§ 04 Delivery

Three phases — useful from day one.

01

Core QC Live

Every station monitored, every pack photographed, every docket searchable. The working system, running in the warehouse.

02

Sharper over time Next

Accuracy analytics and per-station tuning so the system gets better the longer it runs — without calling us back for every adjustment.

03

Connected Planned

Link the QC record to invoices, dispatch and the wider business — on Havit's timeline, at their request.

"Every pack is accounted for — and we can pull the evidence in five seconds instead of half a day."

— Placeholder client quote · Havit Group

Got a similar problem?

If there's a workflow you'd quietly kill for — hours saved, photos you can't find, manual steps that never scale — we'd like to hear about it. Initial conversations are free.

Start a conversation