The Remote Sensing pane watches areas you care about and flags change for you to look at.
What a monitor is
A monitor is a saved watch: an area, something to watch for, a period to compare against, and how often to check. Each run compares what it sees now against that baseline and turns real change into candidates waiting in the Review queue.
Every run tells you plainly how it went — nothing flagged, candidates to review, or that it couldn't see enough to say anything at all.
That last one matters. When cloud or missing imagery means a run can't see enough of your area, it says so instead of reporting an all-clear. Runs also carry warnings — a seasonal mismatch, an implausibly large flagged area — rather than hiding them.
Nothing is accepted for you
Candidates sit in the Review queue until you accept or reject them. There's no automatic path, and no AI path, to acceptance. What you accept becomes a layer in your project, with an evidence trail attached to every decision.
Set up a watch, and change it later.
Task
Compare before and after, and decide.
Task
Run the same analysis on your own imagery.
Task
Look at what imagery exists over an area.
Reference
How it connects
What you accept lands as a vector layer in your project, so everything in Maps & Layers and Analyze & Understand works on it.