Your Mission

You are training Agent Joe, a robot powered by language models, to navigate through mazes. Your job is to write prompts that tell Joe how to make decisions at each step. The better your prompt, the smarter Joe becomes!

How It Works

1. Joe can see in 4 directions: Front, Right, Left, and Behind
2. Joe can move in 4 ways: FORWARD, RIGHT, LEFT, or BACKWARD
3. Joe sees 3 things: "wall" (can't go), "empty" (can go), or "exit" (the goal!)
4. Your prompt tells Joe the rules for choosing which direction to move

Writing Your Prompt

You can write simple rules or complex templates. Use variables to access game state:

• {vision.front}, {vision.right}, etc. - What Joe sees
• {previousActions} - Joe's recent moves and what he saw
• {direction}, {position} - Where Joe is and which way he's facing

Click VARIABLES button for the full list and examples!

Controls

• START: Joe follows your prompt continuously until he finds the exit
• STEP: Joe makes one move at a time (good for testing)
• PAUSE: Pause Joe mid-navigation
• RESET: Start over with a new maze
• SETTINGS: Change models and parameters

Pro Tips

• Start simple! Try: "If Front is empty, go FORWARD. Otherwise, turn RIGHT."
• Use STEP mode to debug why Joe makes certain decisions
• Check the Debug View to see exactly what the language model is thinking

You can use these variables in your navigation prompt:

Available Variables:

• {vision} - Full vision (Front=X, Right=Y, Left=Z, Behind=W)
• {vision.front} - What's in front (wall/empty/exit)
• {vision.right} - What's to the right
• {vision.left} - What's to the left
• {vision.behind} - What's behind
• {direction} - Current facing direction (NORTH/SOUTH/EAST/WEST)
• {position} - Current position as (x, y)
• {position.x} - X coordinate
• {position.y} - Y coordinate
• {moveCount} - Total number of moves made
• {previousActions} - Last 5 moves with vision and actions taken

Example Template Using All Variables:

<think>
I am at position {position}, facing {direction}.
I've made {moveCount} moves so far.
My current coordinates are: X={position.x}, Y={position.y}

Current vision: {vision}
Breaking it down:
- Front: {vision.front}
- Right: {vision.right}
- Left: {vision.left}
- Behind: {vision.behind}

Move history:
{previousActions}
</think>

Analyze the maze state and choose your next action.

Example With Filled Values:

<think>
I am at position (3, 5), facing NORTH.
I've made 12 moves so far.
My current coordinates are: X=3, Y=5

Current vision: Front=wall, Right=empty, Left=empty, Behind=empty
Breaking it down:
- Front: wall
- Right: empty
- Left: empty
- Behind: empty

Move history:
Recent 3 moves (newest first):
[1] Saw: Front=empty, Right=wall, Left=empty, Behind=wall → Action: FORWARD
[2] Saw: Front=empty, Right=wall, Left=wall, Behind=empty → Action: FORWARD
[3] Saw: Front=wall, Right=empty, Left=wall, Behind=empty → Action: RIGHT
</think>

Analyze the maze state and choose your next action.

Note: Variables are replaced with actual values before being sent to the model. You can write simple navigation rules or create complex templates using any combination of these variables.