Create automated surveillance rules via natural language
The agent configures specific detection rules on the surveillance server based on the user's verbal instructions, such as notifying the user when a specific type of vehicle appears or when a person is detected at night.
How it works
The agent uses the 'create rules' tool available in Agent DVR 8.0.7+. It interprets the user's natural language request to determine the detector type (e.g., car, person), the target cameras or groups, the schedule (e.g., sunset to sunrise), and the notification method. The agent then submits the rule configuration to the server, ensuring it aligns with the user's intent and existing system capabilities.
Prompt
Paste this into an agent that has the servers below connected. Adjust the names and dates to your own.
Set up a rule to notify me via push notification if a red car appears on the driveway camera between 6 PM and 9 PM tonight.MCP servers it needs
Source
The vendor page this playbook is drawn from, and the passage that supports it.
Describe what you want to know about, or what should happen, and it sets up a rule on your serverAI Assistants for Security Cameras: Claude, ChatGPT and Gemini with Agent DVR