VECTORIO
EN
EnglishDeutsch

“Oversight wants to know who processed what; one vendor holds the answer”

Auditable data fusion you control.

Data stays within the authority's environment

The problem
  • We rely on one US vendor to fuse our records and legislators are asking why.
  • I must prove who processed which data and why, and today I cannot.
  • Data sits in dozens of case, records and sensor systems with different formats.
With PROTOR
  • Data stays within the authority's environment
  • Auditable record of processing for oversight bodies
  • Integrate fragmented systems without a central platform migration

From today to the first result.

What you do today

records systems from several vendors and one fusion platform

Data sits in dozens of case, records and sensor systems, and who processed which data and why cannot be shown.

With PROTOR

Footage is redacted on the device at 18.7 ms per frame at 30 fps with 0 % drops, and the result is a sealed evidence package anyone can verify.

Your first step

Redact one batch of footage locally and verify the evidence package.

one case batch
How it runs

Body-camera footage, redacted on the device. Step by step.

Faces are detected and blurred frame by frame on the device itself; the result goes out as a sealed evidence package anyone can verify.

PROTOR · Body-camera footage, redacted on the devicerunning
Video File InputVideo.File.SubscriberFace BlurVideo.FaceBlurEvidenceEvidence CollectorPackageEvidence PackOutputBinary File Writer
  1. Video File InputVideo.File.Subscriber
  2. Face BlurVideo.FaceBlur
  3. EvidenceEvidence Collector
  4. PackageEvidence Pack
  5. OutputBinary File Writer
nodes
bodycam-input → Video.File.Subscriber
face-redact → Video.FaceBlur
evidence-collect → Forensic.EvidenceCollector
evidence-pack → Forensic.EvidencePack
evidence-output → BinaryFile.Publisher
18.7 ms per frame · 30 fps · 0 % frame drops · measuredfaces blurred on the devicesealed evidence package
  1. Video File InputReads the footage as one row per frame; pixels travel as a side-car buffer.
  2. Face BlurDetects faces (ONNX, CoreML accelerated) and blurs them.
  3. EvidenceHashes the processed frames into an evidence manifest.
  4. PackagePacks the manifest into a sealed package.
  5. OutputWrites the package to the release folder.

A real workflow from our end-to-end test suite; the designer view is illustrated.

What you get. From the first pilot.

Data stays within the authority's environment

Auditable record of processing for oversight bodies

Integrate fragmented systems without a central platform migration

Why your tools fall short.

×

Closed analytics platforms create vendor and jurisdiction dependency and legal exposure.

×

Generic ETL has no policy/audit semantics.

×

Point integrations do not give auditable lineage.

What drives it
  • German state police legislation and Constitutional Court scrutiny of automated data analysis
  • GDPR / Law Enforcement Directive
  • EU AI Act high-risk obligations for law-enforcement AI

Your pilot. Three steps.

1

Your data shape

Tell us what data you have, where it lives and what the result must be.

2

A scoped pilot

On your data and your hardware, with the success measure written down first.

3

A clear decision

You see the result against that measure — and keep every workflow and record.

Beta · design partners wanted

Bring us your hardest data problem. Let's solve it together.

A short pilot on your data and your hardware. We agree on what success looks like before we start.