The trigger moments that start this conversation, what actually changes on day one and a four-phase plan that keeps every site recording throughout. It also says plainly where a switch is the wrong answer, because these two platforms are built to answer different questions.
The cameras do not move, so switching changes what the software is asked to recognise and how far a detection travels. Both rows describe what each vendor publishes.
Four moments when teams running an identity-led platform start this conversation. If your requirement genuinely is recognising named individuals in real time, none of this applies and you should stay put.
Oosto publishes an identity-led capability set: person of interest alerting, many-to-many face recognition, liveness detection and an access control product that opens guarded points of entry for authorised people. If the day-to-day question on the estate turned out to be what happened at the dock rather than who that was, the platform is being asked a harder question than the site has, and the programme around it is being carried for a requirement that moved.
Oosto published that it was acquired by Metropolis, announced on 22 January 2025, stating that its team and employees would join Metropolis while providing continued support and service to all current and prospective customers and partners. That is the company's own wording and it is not a warning. It is simply the moment a buyer is entitled to ask where the product sits in the new portfolio, and renewal is the cheapest time to ask.
Oosto's published behaviour set covers fighting, falling, running, walking, crouching and lying down, plus line crossing and cross-camera tracking. That is security shaped. If EHS now wants PPE compliance or a forklift near-miss count, or operations wants dock dwell on the same fleet, that is a second vendor unless the platform already covers it.
No speaker, strobe or talk-down behaviour appears on the Oosto pages read, so the escalation path ends with an alert going to a person. On a staffed site that is fine. On an estate with sites nobody watches after 18:00, the detection is worth exactly as much as whoever is available to act on it, and a better model does not close that gap.
The structural differences that decide whether a switch is worth starting.
Swipe the table sideways to see every column.
Oosto data comes from Oosto's own public documentation at oosto.com, including its products and technology pages and its own press release on the Metropolis acquisition, read on August 14, 2026. Where Oosto publishes nothing, this table records the absence rather than guessing at a value.
A rollout that keeps coverage live throughout. Most sites go live inside six weeks.
Start with the requirement, not the fleet. List every use case Oosto currently serves and mark each one identity or not identity, because the identity ones do not migrate and pretending otherwise wrecks the project. Then inventory the cameras per site: manufacturer, model, resolution, codec and network path. Both platforms read cameras you already own, so this phase is a coverage map plus a scope decision, and the scope decision is the one that matters.
Run one site live on both at once. That overlap is the point: it is the only way to compare detection quality and what happens after a detection on identical footage, and it costs one site's licence rather than an estate. Pick a site whose incidents are behavioural rather than identity driven, because that is where the comparison is fair and where the answer is genuinely in doubt.
Move site by site rather than estate-wide, keeping Oosto live at each site until its replacement has passed a full week. Cameras do not move and cabling does not change, so a site cutover is a configuration change plus an IVR. Retire the watchlist and its governance record deliberately rather than by lapse: biometric templates have their own deletion obligations and they do not expire with the subscription.
Once coverage is stable, the work moves from parity to what the previous scope did not reach: adding operations and safety agents on the same cameras, building an Iris detection for something specific to your process and setting what fires at 03:00 when nobody is watching. This phase is where the switch stops being a scope reduction and starts being a wider platform.
The six that come up in every one of these conversations, including the one where the honest answer is do not switch.
No, and it is worth saying so before anything else. Oosto's published capability set is identity led, and Spot AI's published agent set detects events and behaviours rather than matching a person against a watchlist. If real-time recognition of named individuals is a genuine requirement rather than something the estate inherited, this switch does not serve it and a shortlist that pretends otherwise is wasting your time.
Most switches start before the contract ends, because assess and pilot cost little and the comparison is more honest with both systems live. Run the pilot on one site during the overlap and time the cutover to the renewal date rather than paying twice across the estate. Pull your own order form for the notice period in the assess phase.
No, and the plan makes that structural rather than a promise. Oosto keeps running at each site until its replacement has run a full week, the cameras never move and cutover happens site by site. If a site fails its sign-off test, that site stays where it is while the others proceed.
Two separate answers. Footage stays wherever it is recorded today, and Oosto publishes no retention behaviour, so the export list has to come from the recorder rather than from the analytics contract. The watchlist is different: biometric templates and vectors carry their own deletion obligations, and they need a written deletion plan with a date on it rather than being allowed to lapse with the subscription.
Camera reuse is common ground, so it is not the reason to move. What changes is what the platform is asked to recognise, whether the same fleet reaches into safety and operations and where full-resolution video sits. Then there is what happens at the moment of a detection, without a person reading an alert first.
Anyone answering with a number is guessing. What is comparable is scope: quote both against the identical site list and the identical use-case list over three years, and put the compliance work on the same sheet, because a biometric programme carries legal basis, retention policy and consultation costs that a non-identity detection set does not.
Bring a camera list and we will tell you what works as it is.
Customer-reported outcomes from named Spot AI customers.
Staccato went from first conversation to full deployment across an 800-acre campus in seven weeks, on the camera infrastructure it already had.
Bridge33 Capital standardized video across 25 plus properties, each acquisition arriving with a different camera system, and cut footage search from hours to minutes.
The YMCA of Greater Richmond deployed 17 locations in two weeks and standardized retention across the estate.
"Within four minutes of the alarm going off, Spot AI gave us video footage of the incident on the responding officers' phones. We had five recoveries within the hour."
No. Oosto states it is 100% VMS agnostic and Spot AI reads any ONVIF or RTSP IP camera, so any camera feeding one can feed the other. Analog channels that run through encoders or a hybrid recorder today come in through the Intelligent Video Recorder instead. Nothing on the wall moves and no coax is pulled.
Spot AI ships 15+ pre-trained Video AI Agents across security, safety and operations, plus Iris for building a detection specific to your own process, and it acts on what it finds through talk down, strobes and horns on standard speakers already on site. Identity matching against a watchlist is not part of that published set. Establish which of your current use cases depend on identity rather than on behaviour, because that answer decides whether these two platforms are alternatives at all.
Most estates are live inside six weeks: a week to assess, a fortnight of pilot on one site, then site-by-site cutover. Sites go live individually rather than in one switch, so the timeline scales with how many sites you have rather than how many cameras.
It needs a deletion plan with a date, agreed in the assess phase and signed off by whoever owns data protection. Watchlists, templates and vectors are governed separately from video and they do not expire when a subscription does. Treat it as a deliverable of the cutover rather than an administrative tidy-up afterwards.
Oosto published the acquisition itself, announced on 22 January 2025, and stated that its team and employees would join Metropolis while providing continued support and service to all current and prospective customers and partners. Anything beyond that wording is not published, so the roadmap question belongs in a renewal conversation with the vendor rather than on a comparison page.