Games & Simulations: top AI agent use cases

Top Games & Simulations use cases

• GB

  Build four games in parallel with agents

  Four Grok 4.20 agents built a tower defense, mini Factorio, CHIP-8 emulator and roguelike shooter in parallel over a day.

  How it went All four games were completed in one day. The emulator correctly implemented the full opcode set on the first pass.

  Grok Bot5 accounts

• DE

  Build a chess game against a language model

  An early tester asked Devin to build a chess game against a language model; it made good progress but eventually hung.

  How it went Devin made remarkable progress, but at some point it hung and the game wasn't finished. Gao's other tests had mixed results: a Chrome extension worked, and an Antarctic temperature visualization was unsatisfactory.

  Devin

• CX

  Build a racing game from a single prompt

  Codex made a racing game with multiple racers, eight maps and items from one prompt, acting as designer, developer and QA tester by playing it.

  How it went The build produced a racing game with different racers, eight maps and space-bar items, using over 7 million tokens. Earlier iterations are published so you can see how it improved. The source gives no quality assessment.

  Codex4 accounts

• RA

  Build a 3D browser game in 24 hours

  A developer used Replit's agent to build a 3D browser game entirely in the browser with no local setup.

  How it went The readable excerpt stops before any results, so it gives no outcome, numbers or shortfalls. The rest of the article is behind Medium's member-only paywall.

  Replit Agent4 accounts

• GB

  Build and grow a mobile game with bots

  A guide describes six bots building, shipping and improving a mobile game, including uploading ad creatives learned from a recorded click-path.

  How it went He credits the bots with two wins. Cost per install fell from $15 to $1 after the ad was swapped for a partner-focused cut. A hint feature raised D7 retention about 4x. The game passed 1000 downloads in a week.

  Grok Bot2 accounts

• ··

  Compete in a real-time strategy game

  A game environment built for frontier LLMs to play against each other.

  How it went The page gives no scores or numbers. It links to bench results and a hillclimb livestream for StarSkirmish, and the Screeps page covers the tournaments and ladder.

  Custom agent2 accounts

• GE

  Play a button-clicking game via a browser agent

  A developer wired Gemini's Computer Use model to Playwright in Java and had it play a simple button-clicking game to verify click-coordinate scaling.

  How it went The agent clicked the moving button and reported a final score of 10, which confirmed the click handling and coordinate scaling worked. The source mentions no failures in this test.

  Gemini2 accounts

• MA

  Code a 3D plane game in the browser

  A Hugging Face product head prompted Manus to build a Three.js plane-control game and got an animated 3D browser game.

  How it went Mustar called Manus the most impressive AI tool he had tried. The article gives no technical results, game details, or limitations for this test.

  Manus2 accounts

Questions

What kinds of game jobs are these?

Some agents play a game, some build one, and some test one. The entry says which.

How many Games & Simulations use cases are there?

There are 48 use cases in this category on the site right now. This page shows the top ones, not the full set.

Which agents show up most for this kind of work?

The named agents used most often here are Grok Bot, Gemini and Claude Code. Other entries use a custom-built or unnamed agent.

How does a use case get onto this page?

It has to be something a person reported doing. We re-read the source before it is shown. Reader submissions are reviewed by a person first. An approved submission is checked against its source and added in a later update. A rejected one is not added.

How is this list ordered?

By votes from people on this site. More votes means higher on the list. Ties go to the use case described in more separate accounts.