Bot Plays Puzzles with Jev

Michaël Ménard built a bot that uses Jev to choose taps in a puzzle game. It played 15 puzzles with 190 API calls, at ~240 ms per call and a total cost of $0.0298.

View on X cost$0.0298time~240 ms per call

Michaël Ménard@mikemenard_com𝕏

I built a bot that plays a puzzle game by asking an AI before every tap. Each tap you see is a live API call. This is Jev, @typesafeai model. No prompt, no generated text. My code lists the legal taps, Jev returns a probability for each, code taps the best one. 15 puzzles, 190 calls, ~240 ms per call, total cost $0.0298. (Most of that was the last hard puzzle) Why so fast and cheap? A normal LLM a

Sep 18, 2026X postsView on X

The code lists the legal taps, and Jev returns a probability for each. The bot taps the option with the highest probability; it uses no prompt or generated text.

Also filed under Games & real time

Steer a 3D Box with Goals
The build steers a 3D box with plain-language goals. An LLM plans each instruction, while TypeSafe Jev makes move, turn, and jump decisions in real time.
Benchmarks Jev on Pokémon Red
The project benchmarks Jev, TypeSafe’s fast decision model, against Jev paired with a GPT-6 Sol planner for playing Pokémon Red.
Plain-English Cellular Ecosystem Simulator
LifePot is a cellular automaton-inspired ecosystem that users describe in plain English. Jev turns those inputs into species, feeding relationships, reproduction strategies, and environmental conditions.
Mapping Children's Behavioral Intent in Games
Mores Research used Jev to map children’s behavioral intent in games and examine how it correlates with real-world behavior. It reports mapping intents across 45+ real sessions involving 20 child users over a long horizon.