I have ten known bugs and two days, which ones should the AI fix first

A dramatic bug in a corner few players reach can matter less than a small one on the main path. This entry ranks bugs by how bad they are, how many players really meet them and how long the fix takes, with game-stopping ones always on top.

Why this works

Your time is limited, so the right question is how much harm you remove per hour, not how ugly a bug looks. Harm is how bad it is times how many players actually walk into it, and anything that blocks the ending is a different class.

When not to use it

Do not follow the ranking for bugs that damage players' saves or money, or that break trust, even if few meet them. Also the shares are guesses until you have real play counts, so treat close scores as ties.

In the full entry

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

Say this to your AI

Use the Spielerando entry "I have ten known bugs and two days, which ones should the AI fix first" (read_entry which-bug-first-by-who-meets-it) 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