He set a rule: When main_entrance.counts.in exceeds 200 people in 5 minutes, send an alert to security and trigger a digital sign outside saying "EAST ENTRANCE IS LESS BUSY". The webhook payload was minimal:
“Here’s your API documentation,” he said. “Good luck.”
It wasn’t.
The API endpoint GET /dwell-times for the "north corridor" showed an average stay of . That was too low. People should linger near the new bookstore and the coffee cart.
Most paths were straight lines: people walked through. But one repeated pattern caught his eye: a sudden stop at coordinate [x: 214, y: 87] , then a rapid reversal. xovis api documentation
{ "zone": "main_entrance", "interval": "2025-03-10T14:00:00Z", "in": 847, "out": 812, "net": 35 } For the first time, he knew exactly how many people were inside. Two weeks later, Alex noticed something strange.
The response returned an array of trajectories—each a list of coordinates over time. He set a rule: When main_entrance
Alex didn’t know. He had old infrared beams at entrances that counted shadows, not people. On rainy days, they double-counted umbrellas. On busy Saturdays, they missed families entirely.
