Session pacing
Your AI shows the rhythm of a play session: how long people play, what they spend the time on, where nothing happens for a long while, and what they were doing when they stopped. It also measures how long it takes to reach a moment that matters, such as the first fun bit, and compares all of it with your plan.
When you need it
When a game feels slow or people drift away without losing, and when you want to know how long the first fun takes to arrive. Quiet stretches are only a problem if they are not meant to be there, so compare them with your plan.
Say this to your AI
Use session pacing from Spielerando on my event log. First write down the rhythm I want as a Mermaid state diagram: the kinds of activity, the order, roughly how long each should last, and when the first fun moment should arrive. Then compare the real session lengths, time shares, quiet spots and last events with that plan. Show me the numbers each finding rests on. A quiet spot is only a question, so say what you cannot know from a log, and say so if there are too few sessions.Or skip this and connect the MCP: your AI then finds all of this by itself.Connect the MCP
Settings
- gapSeconds (60): A gap between two events of at least this many seconds counts as quiet.
- minSessions (30): Under this many sessions, the report calls the numbers rough.
- windowMinutes (5): The width of a window in the still-playing list, in minutes.
Your AI gets the code
The finished code and math come through the Spielerando connection, so your AI can use them right away. Connect your AI
Common questions
is my game too slow
Look at where the log goes quiet for a long time and whether people stop soon after. Compare that with what you meant to happen there, because a long gap can also be someone reading happily.
how long do people play my game
Use the middle session length, not the average. One person who left the game running for hours would pull the average up and tell you nothing.
how do i measure time to first fun
Pick the moment that counts as fun, write an event for it, and measure the time from the start. Then look at how many reach it at all.