Most of our reports are played once. We ask a question, build the game, play it, and write up what happened. Then the world moves on and the report stays where it was.

A perpetual game is a game we play again on a fixed public calendar, and check against what really happened each time. The calendar belongs to the world, not to us. A central bank meets on published dates. A government announces its borrowing every quarter. Each of those dates is a point where the game’s claims can be marked right or wrong by anyone with the public record.

The weeks between two of those dates are a cycle. Inside a cycle we play the game at least once, with every start value reset to that day’s record. When the cycle closes, we mark the claims, write down what the game got wrong, and open the next one.

What it is useful for

A dated record instead of an opinion. A report played once can say what it thinks. It cannot say how often it was right, because nobody checked. A perpetual game writes each claim down with the date it was written and the date it resolves, before the answer is known. After a few cycles you can read the record and decide for yourself how much to trust the next one.

A check on the mechanism, not just the call. The most useful thing a cycle can tell us is that something happened which no player in the game could have done. We call that a surprise. A surprise means the game was missing a move, or a player, and it means that whether or not the call came out right. Getting the answer right through the wrong mechanism is luck, and a perpetual game is built to notice the difference.

A question that keeps coming back. Some questions do not close. What a central bank does about the long end of the debt market is one. What a regulator does with a new power is another. If your organisation has a question like that, a perpetual game gives it a standing brief that is re-played on the dates that matter and read against the record each time.

How it improves itself, and why slowly

Every closed cycle becomes a frozen, replayable fixture: the same game, the same dice, and what the report said. The fixtures together are the archive. Before we change any rule of the game, we replay every fixture in the archive under the new rule. If a finding we published in an earlier cycle flips, the change stops until we can explain the flip in writing and correct the earlier report. A change that quietly rewrites history is the failure we are guarding against, not the goal.

A defect is anything a cycle shows the game got wrong: a surprise, a move that fired for the wrong reason, a player that never did anything. A defect has to be seen twice, in two different cycles, before it can move a rule. One surprise is noise. Two is a pattern. And every change is written up before it is made, with a prediction of what it will fix and a condition under which we will undo it. Programs play the game. A named person changes it, and there are few of those.

The arithmetic does the rest. Before a rule can change in the fourth cycle, the three earlier cycles must replay with no published finding flipped. By the twelfth cycle, eleven must. The game gets harder to change as it gets older, which is what a record is for.

That makes improvement slow. A handful of rule changes a year, each with a written reason and a replayed archive behind it. We think that is the right speed for anything that goes out with our name on it. (It is also the speed at which we can read everything we wrote.)

What it does not claim

A perpetual game is not a forecast, and its numbers are not probabilities. When a report says an outcome happened in, say, nine of twelve games, that is a count over games we wrote, under a plan we chose for one player. Change the plan and the count changes. The plan is the forecast, and the plan is a human choice. The record page marks which outcomes follow from the plan and which come from the play.

The story you read in a perpetual report is written from a game played by AI models, one seat each. The record is kept on the games played by rules alone, where only the dice change. We keep the two apart on purpose, and the report marks any line in the story that the games played by rules alone do not also support.

Whether any of this tracks the world is a question for the validation page, not for this one.

What you will see each cycle

• A notice on the report saying which cycle it is, when the claims were written, and when they resolve.
• A record page with every claim, dated, and how many games it came from.
• A short review when the cycle closes: what resolved which way, what surprised the game, what changed.
• A correction on any earlier report whose published finding a change has flipped.