diff --git a/modules/source/02_activations/activations_dev.py b/modules/source/02_activations/activations_dev.py
index 63f7ffa1..50352c24 100644
--- a/modules/source/02_activations/activations_dev.py
+++ b/modules/source/02_activations/activations_dev.py
@@ -342,6 +342,10 @@ class ReLU:
         return Tensor(result)
         ### END SOLUTION
 
+    def __call__(self, x: Tensor) -> Tensor:
+        """Allows the activation to be called like a function."""
+        return self.forward(x)
+
     def backward(self, grad: Tensor) -> Tensor:
         """Compute gradient (implemented in Module 05)."""
         pass  # Will implement backward pass in Module 05
@@ -456,6 +460,10 @@ class Tanh:
         return Tensor(result)
         ### END SOLUTION
 
+    def __call__(self, x: Tensor) -> Tensor:
+        """Allows the activation to be called like a function."""
+        return self.forward(x)
+
     def backward(self, grad: Tensor) -> Tensor:
         """Compute gradient (implemented in Module 05)."""
         pass  # Will implement backward pass in Module 05
@@ -580,6 +588,10 @@ class GELU:
         return Tensor(result)
         ### END SOLUTION
 
+    def __call__(self, x: Tensor) -> Tensor:
+        """Allows the activation to be called like a function."""
+        return self.forward(x)
+
     def backward(self, grad: Tensor) -> Tensor:
         """Compute gradient (implemented in Module 05)."""
         pass  # Will implement backward pass in Module 05
@@ -710,6 +722,10 @@ class Softmax:
         return Tensor(result)
         ### END SOLUTION
 
+    def __call__(self, x: Tensor, dim: int = -1) -> Tensor:
+        """Allows the activation to be called like a function."""
+        return self.forward(x, dim)
+
     def backward(self, grad: Tensor) -> Tensor:
         """Compute gradient (implemented in Module 05)."""
         pass  # Will implement backward pass in Module 05
diff --git a/modules/source/03_layers/layers_dev.py b/modules/source/03_layers/layers_dev.py
index 32b2e7bd..abd452d7 100644
--- a/modules/source/03_layers/layers_dev.py
+++ b/modules/source/03_layers/layers_dev.py
@@ -477,6 +477,10 @@ class Dropout:
         return Tensor(output_data)
         ### END SOLUTION
 
+    def __call__(self, x, training=True):
+        """Allows the layer to be called like a function."""
+        return self.forward(x, training)
+
     def parameters(self):
         """Dropout has no parameters."""
         return []
diff --git a/modules/source/04_losses/losses_dev.py b/modules/source/04_losses/losses_dev.py
index b9ace1bd..afffc012 100644
--- a/modules/source/04_losses/losses_dev.py
+++ b/modules/source/04_losses/losses_dev.py
@@ -50,8 +50,6 @@ Let's measure prediction quality!
 ```python
 # Final package structure:
 from tinytorch.core.losses import MSELoss, CrossEntropyLoss, BinaryCrossEntropyLoss, log_softmax  # This module
-from tinytorch.core.tensor import Tensor  # Foundation
-from tinytorch.core.layers import Linear, Sequential  # What makes predictions
 ```
 
 **Why this matters:**
@@ -433,6 +431,10 @@ class MSELoss:
         return Tensor(mse)
         ### END SOLUTION
 
+    def __call__(self, predictions: Tensor, targets: Tensor) -> Tensor:
+        """Allows the loss function to be called like a function."""
+        return self.forward(predictions, targets)
+
     def backward(self) -> Tensor:
         """
         Compute gradients (implemented in Module 05: Autograd).
@@ -610,6 +612,10 @@ class CrossEntropyLoss:
         return Tensor(cross_entropy)
         ### END SOLUTION
 
+    def __call__(self, logits: Tensor, targets: Tensor) -> Tensor:
+        """Allows the loss function to be called like a function."""
+        return self.forward(logits, targets)
+
     def backward(self) -> Tensor:
         """
         Compute gradients (implemented in Module 05: Autograd).
@@ -808,6 +814,10 @@ class BinaryCrossEntropyLoss:
         return Tensor(bce_loss)
         ### END SOLUTION
 
+    def __call__(self, predictions: Tensor, targets: Tensor) -> Tensor:
+        """Allows the loss function to be called like a function."""
+        return self.forward(predictions, targets)
+
     def backward(self) -> Tensor:
         """
         Compute gradients (implemented in Module 05: Autograd).