AI games, without the slop
Reviews of AI story games, character chat apps and AI companions, tested past the first hour.
The first hour is always fun. We keep playing until the writing repeats, the characters drift, the details slip, the story stalls or the price starts climbing, then we score what broke and show you the lines that prove it.

The Slop Meter
Every app gets a Slop Score from 0 to 100.
Lower is better.
Our slop counter found no stock phrases in this one.
Receipts or it didn't happen
Scores aren't based on vibes.
When we flag something, we show the lines that triggered it and when the test was run. You can see the evidence and decide whether you agree.
Tested by people. Counted by code.
People run the conversations and judge whether the product is any good.
Our tools handle the boring part: tracking repeated phrases, stock descriptions, forgotten details, looping plots, and other patterns across the test.
The score comes from the test, not from somebody picking a number afterward.
We run our own copy through it too
PromptPlay pages go through the same slop checks before they ship.
You'll see the result on the page.
Featured rankings
Latest reviews
Five kinds of slop, one Fun Meter
Every review scores up to five axes from 0 to 100, lower is better. Each one answers a single question.
Does it write like a person?
Best: Specific, varied writing. Stock phrases are rare, and people write or edit what you read.
Does it remember you?
Best: Remembers specific events across sessions, by design.
Does everyone sound the same?
Best: Distinct, consistent voices written or edited by people.
Does anything happen?
Best: Authored plots with stakes, branches and endings.
Does it charge you for caring?
Best: Free or one flat price, with no limit that interrupts a scene.
Is it any fun?
0 to 10, higher is better. 9 and up: Can't put it down.
New on PromptPlay
Slop check: passedThis page went through our slop counter before publishing. How we check our own copy
