Noonlight has announced significant updates to its Verify API, enhancing its video monitoring solutions with two new key features aimed at improving security for both commercial and residential providers. These enhancements aim to deliver enhanced protection by allowing more proactive management of video security systems.
The Verify API provides a layer of human verification to video-triggered events, enabling Noonlight agents to assess incidents before deciding on emergency dispatch.
This integration pairs advanced analytics with professional monitoring to minimise irrelevant video distractions and enable quicker responses to real threats, all without increasing false alarms or operational demands.
Introduction of new AI features
The updates introduced by Noonlight include an AI Person Filtering feature, which screens video events by automatically discarding clips without any detected individuals. This innovation eradicates the need for evaluating empty motion alerts. Additionally, when an event warrants escalation to a live agent, the Advanced Verification feature offers comprehensive context with extended video footage and live camera access, allowing agents to address and deter potential incidents in real time even before an alarm is set off.
This leads to fewer unnecessary disturbances for users, reduced unwarranted police dispatches, and effective alarm resolution when critical.
Mitigating emergency situations
John Tassone, President of Noonlight, indicated, "The burden of responding to an emergency should never fall on the end user, and unnecessary disruptions should never affect the people our partners are trying to protect.”
He further stated, “What we’ve built is a smarter way to deliver the right context to agents at exactly the right moment — so they can filter out the noise, act decisively on real situations, and prevent emergencies from escalating wherever possible. That’s what automatic safety looks like in practice.”
AI person filtering capabilities
Noonlight uses AI to filter video clips so only actionable footage reaches monitoring agentsNoonlight utilises a proprietary AI model that evaluates all incoming video clips, swiftly dismissing any where a person is not detected, thereby ensuring non-actionable footage never reaches monitoring agents. By processing hundreds of frames per video clip, the AI model boasts a 99% recall and a 97% precision rate, ensuring minimal human appearances are not overlooked.
For existing partners using AI-based filtering, Noonlight’s enhanced model provides further noise reduction, especially in outdoor settings, supporting both vendor consolidation and reducing necessary integrations to manage.
Advanced verification and its benefits
The Advanced Verification tool augments Noonlight’s current verification processes by giving agents additional context, such as footage up to 90 seconds before an incident along with a live view from the camera. This allows for faster threat assessment and decision-making without immediate emergency dispatch.
Agents can also employ active deterrence through real-time communication directly via the camera, defusing situations before alarms necessitate immediate emergency response. This capability significantly enhances intervention speed, delivering a more efficient user experience without sacrificing security.
Preliminary data suggests these advanced verification tools with talkdown capabilities reduce false alarms by 45%, with 37% resulting in individuals leaving the vicinity independently and 8% identified as authorised personnel, significantly preventing unnecessary alarms.
