Which story moment makes people leave the session, beyond normal leaving?

People leave online sessions all the time, so a count of leavers after a scene proves nothing. A scene is only a problem if more leave after it than would have left anyway. This entry shows a fair baseline and a way to avoid blaming scenes with too little data.

Why this works

People leave at every moment for ordinary reasons, so a raw count blames whatever scene comes first. Only the surplus over the usual leaving is a signal, and only when enough people were there to trust it.

When not to use it

Do not use it with only a handful of sessions, where one early dinner call can fake a problem. Also not when you can simply ask players: a short question after the scene beats any statistic on small groups.

In the full entry

• What to build, step by step
• Starting values and the reason for each
• 3 common mistakes and the fix
• 41 lines of example code with 4 checks that pass
• How your AI shows you that it works

Say this to your AI

Use the Spielerando entry "Which story moment makes people leave the session, beyond normal leaving?" (read_entry story-beats-that-make-players-leave-the-session) in my game. Build it step by step, and show me how you checked that it works.

Or skip this and connect the MCP: your AI then finds all of this by itself.Connect the MCP