FAQ
Questions, answered
The things insurers and brokers ask us most. If your question is not here, just ask.
Technology and deployment
Does it work with existing CCTV?
In most cases, yes. The platform works with nearly all existing cameras over standard network protocols, so there is usually no need to replace anything. The software can run on a small on-site device (edge) or through secure cloud processing.
How quickly can a site be up and running?
Setup is straightforward and insights typically start flowing soon after. The exact timeline depends on the number of cameras, the use cases, and whether any hardware is needed for on-site processing.
How do you keep false positives low?
Detection is tuned to each site, with configurable parameters so sensitivity matches the operational context and risk appetite. The AI models are also continuously fine-tuned, so accuracy improves over time and alerts stay relevant to the people who act on them.
What hardware is needed?
Either a small on-site compute device for edge processing, or the cloud option which needs no additional hardware. Requirements depend on the number of cameras and use cases.
Privacy and data
What about GDPR and privacy compliance?
Privacy is designed in from the start. Deployments follow data minimisation and privacy-by-design principles, process footage only for the agreed risk use cases, and are configured to meet UK GDPR, including a data protection impact assessment where appropriate. Data residency is agreed as part of each deployment, with UK and EU hosting available so footage and detection data stay in-region.
Who owns the data, and who can see it?
The customer owns their data. It is shared with insurers only under clear policy terms and with explicit consent, and faces are blurred by default so the system reads behaviour and hazards rather than identities.
Does the system identify individuals?
It is not designed to identify people. Facial blurring is applied by default, and the focus is on detecting risk events and unsafe conditions, not recognising who is on camera.
What it detects
What use cases can it detect?
More than thirty in total, spanning safety and PPE, fire and water, security and intrusion, underwriting validation, and operational insight. The website shows a cross-section, and the full list is available on request.
Can it validate what a customer declared at underwriting?
Where agreed as part of the product, the analytics can surface site conditions or behaviours that differ from what was declared at placement or renewal, supporting more accurate underwriting.
Commercial and getting started
What are the costs involved?
Software pricing starts from £15 per camera per month, with no upfront fee. Exact pricing is confirmed against the final requirements, as it depends on how the camera streams are processed and the number of use cases being monitored. Any hardware needed for on-site (edge) processing is additional and depends on the site. In most cases the claims prevented outweigh the combined cost of software and hardware.
Who provides the AI technology?
The detection engine is developed by our technology partner, a specialist video analytics company whose platform already runs on industrial sites internationally. Mitigate It does not build the AI: we package the proven engine for the insurance market, and support insurers, brokers and policyholders end to end.
How does an insurer or broker get started?
We supply and run the AI CCTV software alongside the cover you already write or place; your product and wordings stay in your control. Brokers are onboarded and trained at no fee. The For insurers and For brokers pages explain how the partnership works, and a demo is the quickest way to see it in action.
What support do you provide?
Setup, configuration, team onboarding and ongoing software updates are included. Dedicated account support is available for larger deployments.
Still have a question?
Book a short demo and we will answer anything specific to your book, your risks or your compliance requirements.