diff --git a/.cursorrules b/.cursorrules
new file mode 100644
index 00000000..fa6aad38
--- /dev/null
+++ b/.cursorrules
@@ -0,0 +1,163 @@
+# NBDev Educational Pattern for TinyTorch Modules
+
+When working with module development files (`*_dev.py`), follow this educational structure:
+
+## File Format
+Use Jupytext percent format with NBDev directives:
+
+```python
+# ---
+# jupyter:
+#   jupytext:
+#     text_representation:
+#       extension: .py
+#       format_name: percent
+#       format_version: '1.3'
+#       jupytext_version: 1.17.1
+# ---
+
+# %% [markdown]
+"""
+# Module X: Title - Brief Description
+
+Educational introduction and learning goals...
+"""
+
+# %%
+#| default_exp core.component_name
+
+# Setup and imports
+import required_libraries
+
+# %% [markdown]
+"""
+## Step 1: Concept Explanation
+Educational content explaining the concept...
+"""
+
+# %%
+#| export
+class ComponentName:
+    """
+    Component description.
+    
+    TODO: Student implementation instructions.
+    """
+    def method(self):
+        raise NotImplementedError("Student implementation required")
+
+# %%
+#| hide
+#| export  
+class ComponentName:
+    """Complete implementation (hidden from students)."""
+    def method(self):
+        # Actual implementation
+        pass
+```
+
+## Key NBDev Directives
+
+- `#| default_exp core.module` - Sets export destination in tinytorch package
+- `#| export` - Marks code for export to package
+- `#| hide` - Hides cell from students (instructor solution)
+- `# %% [markdown]` - Markdown cells for explanations
+- `# %%` - Code cells
+
+## Educational Structure
+
+### 1. **Conceptual Foundation** (REQUIRED)
+Each module must start with clear conceptual explanations:
+
+```markdown
+## Step 1: What is [Concept]?
+
+**Definition**: Clear, simple definition with examples
+**Why it matters**: Real-world motivation and ML context
+**How it works**: Intuitive explanation before math
+**Visual examples**: Concrete examples, diagrams, analogies
+**Connection**: How it builds on previous modules
+```
+
+### 2. **Guided Implementation** (REQUIRED)
+Instead of just `raise NotImplementedError`, provide:
+
+```python
+def method(self):
+    """
+    TODO: Step-by-step implementation guide
+    
+    HINTS:
+    1. First, think about what this method should return
+    2. Consider the data types and shapes involved
+    3. Start with a simple case, then generalize
+    
+    EXAMPLE:
+    Input: [describe input]
+    Expected output: [describe expected output]
+    """
+    # Step 1: [specific guidance]
+    # Step 2: [specific guidance] 
+    # Step 3: [specific guidance]
+    raise NotImplementedError("Student implementation required")
+```
+
+### 3. **Standalone Learning** (REQUIRED)
+Each module should be self-contained:
+- Brief concept review (even if covered in textbook)
+- Clear motivation for why this matters
+- Concrete examples before abstract implementation
+- Connection to previous modules and next steps
+
+### 4. **Educational Flow** (REQUIRED)
+Follow this structure for every module:
+
+1. **Concept → Motivation → Intuition → Implementation → Testing**
+2. **Visual examples** (shapes, transformations, operations)
+3. **Real-world analogies** (containers, functions, pattern matching)
+4. **Scaffolded complexity** (start simple, build up)
+
+### 5. **Implementation Guidance** (REQUIRED)
+For each TODO section, include:
+
+```python
+"""
+TODO: [Clear task description]
+
+APPROACH:
+1. [First step with specific guidance]
+2. [Second step with specific guidance]
+3. [Third step with specific guidance]
+
+EXAMPLE:
+Input: [concrete example]
+Expected: [concrete expected output]
+Your code should: [specific behavior description]
+
+HINTS:
+- [specific hint 1]
+- [specific hint 2]
+- [specific hint 3]
+"""
+```
+
+### 6. **Testing and Feedback** (REQUIRED)
+Include immediate testing cells:
+- Simple test cases with expected outputs
+- Clear error messages for debugging
+- Progressive complexity (simple → complex)
+- Visual verification where possible
+
+## Naming Convention
+
+Module files should be named `{module_name}_dev.py` to indicate development notebooks, following the established pattern from [modules/setup/setup_dev.py](mdc:modules/setup/setup_dev.py) and [modules/tensor/tensor_dev.py](mdc:modules/tensor/tensor_dev.py).
+
+## Educational Principles
+
+1. **Build → Use → Understand → Repeat**: Each module should follow this cycle
+2. **Immediate Feedback**: Students should see results quickly
+3. **Concrete Before Abstract**: Start with examples, then generalize
+4. **Scaffolded Learning**: Provide hints and guidance, not just empty functions
+5. **Standalone Modules**: Each module should be understandable independently
+6. **Visual Learning**: Include diagrams, examples, and visualizations
+7. **Real-world Context**: Connect to practical ML applications 
\ No newline at end of file