Skip to content
Focient

Wet night intersection, by Ricky Esquivel on Pexels (Pexels License).

Police and public safety · 02:30

Your night shift, from the desk

Scrubbing recordings, camera by camera.

The live dashboard shows your cameras, with the most significant recent events above them.

An example live dashboard: three recent events listed under Needs your attention, six camera tiles each marked LIVE, and a bar for asking a question at the bottom. The places and times are fictional.

Screens on this page show fictional data.

Wet night intersection, by Ricky Esquivel on Pexels (Pexels License).

At 02:47

An alert reaches the desk

A time-in-zone rule names a zone and a schedule.

Each event from a live camera is checked against your rules as it is recorded, and a matching alert is sent at that point.

An example event, as the event detail shows it: a snapshot of the side door at the loading dock at 02:47:13, marked Verified, the written description that the rule's check read, and a question asking whether the alert was useful, with Useful and Not useful buttons. The data is fictional.

Wet night intersection, by Ricky Esquivel on Pexels (Pexels License).

At 03:40

Then a question for the cameras

Ask in plain language about what your cameras saw, and answers come with citation cards for the events and frames they rest on.

Each answer comes with a snapshot of the exact frame the vision model judged.

An example Ask screen. The question is "What happened at the loading dock last night?" The answer names the events by camera and time and cites 2 events under Sources, each with its snapshot, its rank and a Verified chip. The data is fictional.

Ranked by how closely this matches your question. Not a probability.

Wet night intersection, by Ricky Esquivel on Pexels (Pexels License).

At 05:30

What you found goes into a case

A case holds a timeline across cameras, annotations and a relationship map.

A case briefing is drafted for an analyst to review and can be exported as a Markdown file.

A case's Timeline screen: the dock door opens and closes, and a white van stops at the gate, each with its time, camera and snapshot. The data is fictional.

Alerts on the desk

Your operators mark each alert useful or not, and every rule keeps a quality score.

An example alert rule, as the rule editor shows it. It is an event rule for camera 03, the loading dock. It matches events tagged after hours and door, and carries a plain-language check: Confirm the side door is open. The data is fictional.
  • Screened first

    Frames are sampled from each camera and screened first, and only the frames that pass are described in words.

  • Where alerts go

    Alerts go out by email, or to a system your administrator connects.

  • Who is on the desk

    People on your desk hold an administrator, operator or auditor role, and administrators and auditors can read an audit log.

How alerts are set up

Ask across the grid

Describe what you are looking for in plain words.

An example search, as the search palette shows it. The description white van stopped at the dock gate after midnight is typed into the search field. Two events and two frames are listed under Events and Frames in rank order, each with its camera and the frames with their time. No score or percentage is shown. The data is fictional.
  • Your time zone

    Time phrases such as "last night" resolve in the organisation's time zone, or in UTC if none is set.

  • Vehicle search

    Vehicles can be searched by type, colour, make, markings and damage.

  • Checked again

    The hash of a snapshot is recorded as it is captured, and a "Verified" chip on a citation checks it again.

How evidence is checked

Questions police teams ask

Can we use the cameras the station already has?

It works with the RTSP cameras you already run, with no new hardware.

Who can open a case file?

Only the members of a case can see it, as owner, editor or viewer, and an administrator's break-glass access is audited.

What does the system say about the people it sees?

Rules and labels say what happened on camera. The privacy rules are set out on the Trust page.

Where would it run for us?

We answer questions about deployment, networks and data flow in the first conversation, under NDA.

What does a pilot need from us?

A pilot needs a named owner, your camera and network details, and the questions your team wants answered.

How a pilot works

  1. Tell us about your camera grid and the questions your team asks most.
  2. A pilot runs on your own cameras, with your team, against criteria agreed before it starts. We agree the scope together: which cameras, which questions, and how the pilot will be judged.
  3. We connect your cameras with your team.
  4. During the pilot, your operators use it on your cameras. At the end, your pilot owner reviews the results against the criteria agreed at the start.

Talk to us about your night shift

Tell us which cameras and which hours matter most to your team.

Request a demo

Start with one station or precinct.