Human expertise. Preserved for the future.

Capture real world skills. Build the data foundation for physical AI.

Why Vigil

01

The problem

Manuals and training videos miss what experts actually do: the small adjustments, the order of steps, the judgement calls made in real conditions.

02

What matters

Real demonstrations of real work, captured where it happens: on busy sites, in changing conditions, from the person doing the job.

03

Vigil

A physical AI data platform that captures skilled work from the worker’s perspective and is being built to prepare demonstrations for robot learning and searchable team knowledge.

Language models learned from libraries of written text. The skill in a pair of hands was never written down.

Vigil captures what manuals miss.

Meet Vigil.

Built for the physical world.

Capture what matters.

Turn experience into knowledge.

Your knowledge. Under your control.

Built for the future of physical intelligence.

Human expertise. Preserved for the future.

How it works

From real work to data for physical AI.

  1. 1

    Clip it on

    Vigil clips to the brim of a hard hat or cap. No screens, no menus, nothing to hold.

  2. 2

    Work as usual

    Start and stop with your voice or the single button. The camera, depth and motion sensors record the task from your point of view.

  3. 3

    It uploads itself

    Recordings wait safely on the device and upload over wireless internet or LTE as soon as a connection is available.

  4. 4

    Find any moment

    Each demonstration becomes searchable task episodes with timestamps, ready to review, reuse and export.

Everyday tasks.
A view from the worker’s perspective.

Vigil clips to your cap, leaving both hands free for the task.

A woman folding a shirt with Vigil clipped to the brim of her cap
A man washing a plate with Vigil clipped to the brim of his cap

Two ways to take part

Put expertise on the record.

Capture it for your own team, or contribute your skills and get paid for them.

For organisations

Preserve your team’s expertise.

  • Capture demonstrations on your own sites
  • Process recordings on your own infrastructure, with the AI models you approve
  • Search, review and export reusable task knowledge
  • Turn your best demonstrations into training data for your robots
Explore the shop

For individuals

Record your skills. Get paid.

  • Receive clear recording tasks
  • Record without using your hands with Vigil on your cap
  • Get paid for accepted demonstrations
Become a Ranger
A human motion trace resolving into a robotic arm

Physical AI

Teach robots how the work is really done.

Robots need examples of work in the real world. Vigil captures skilled people performing tasks from their own perspective and is building a pipeline to prepare those demonstrations for robot learning.

  • Demonstrations from the worker’s perspective

    Video from the wearer’s point of view, with depth and head motion captured alongside: how the task looks to the person doing it.

  • Organised into tasks

    Recordings become episodes and steps with timestamps, so a robot learning team gets clean examples, not hours of raw footage.

  • Real conditions, at scale

    Real sites, real tools, real variation. The messy detail that lab demonstrations miss and robots most need.

  • Ready for robot learning

    Export curated episodes as datasets for training robot policies and physical AI models, on your terms.

Private by design

Your knowledge. Under your control.

Vigil can run entirely inside your environment. Recordings, transcripts, annotations and search indexes stay on infrastructure you own.

  • Bring your own models

    Connect the AI services your company already approves. Nothing is sent to ours.

  • No silent fallback

    If a model is unavailable, recordings simply wait. Nothing is routed elsewhere.

  • Every result is reviewable

    Annotations keep their evidence, versions and reviewer decisions.

  • Export when you choose

    Datasets leave your environment only when you export them.

Recorded demonstrations moving into a private, bounded archive

Under the hood

Built for the physical world.

A compact module that clips to the brim of a hard hat or cap, carrying the sensors that matter for capturing skilled work.

The Vigil device, angled view
Camera
Sees the task from the wearer’s point of view.
Depth sensing
A multizone time of flight sensor measures distance to hands, tools and surfaces.
Motion sensing
A motion sensor records head movement across six axes alongside the video.
Voice and button
Start, stop and mark moments without touching a screen.
Light and sound
A status light and a tone confirm when Vigil is recording.
Integrated flash
A forward light for dim spaces and tight corners.
Always connected
Uploads over wireless internet, with optional LTE for the field.
Fits the job
Clips to a hard hat or cap and stays out of the way.

The film

Twenty seconds on why expertise deserves a record.

Every task, seen through the eyes of the person who knows it best.

Bring Vigil to your team and start capturing the real world expertise that can power robot learning and team knowledge.