diff --git a/.env-example b/.env-example
deleted file mode 100644
index 928533d..0000000
--- a/.env-example
+++ /dev/null
@@ -1,2 +0,0 @@
-DATABASE_URL=your-database-url
-OPENAI_API_KEY=your-openai-api-key
\ No newline at end of file
diff --git a/prisma/schema.prisma b/prisma/schema.prisma
index a320a24..d9bc5b1 100644
--- a/prisma/schema.prisma
+++ b/prisma/schema.prisma
@@ -26,7 +26,7 @@ model Task {
   id          String    @id @default(cuid())
   title       String
   description String
-  status      TaskStatus
+ status      TaskStatus @default(TODO)
   priority    Priority
   dueDate     DateTime?
   assignedTo  String?
@@ -48,6 +48,7 @@ model Subtask {
   task        Task     @relation(fields: [taskId], references: [id], onDelete: Cascade)
   createdAt   DateTime @default(now())
   updatedAt   DateTime @updatedAt
+  
 
   @@map("subtasks")
 }
diff --git a/services/aiService.js b/services/aiService.js
index 043f837..0ea83df 100644
--- a/services/aiService.js
+++ b/services/aiService.js
@@ -71,45 +71,98 @@ export function extractTaskFromAIResponse(responseContent) {
  * @returns {Object} Parsed and validated task data
  */
 export async function generateTaskWithAI(prompt) {
-  // TODO: STUDENT TASK - Complete this function to generate tasks using AI
-  //
-  // Instructions:
-  // 1. Check if the OpenAI API key is configured in environment variables
+  try {
+    // TODO: STUDENT TASK - Complete this function to generate tasks using AI
+    console.log("Generating task with AI...");
+    //
+    // Instructions:
+  // 1. Check if the OpenAI API key is configured in environment 
+  // variables
   //    - Use process.env.OPENAI_API_KEY
   //    - Throw an error if not configured
+  if (!process.env.OPENAI_API_KEY) {
+    throw new Error("OpenAI API key is not configured");
+  }
+
   //
   // 2. Create a system prompt that tells the AI what to do:
   //    - Explain that it's a task management assistant
-  //    - Ask it to create a task with subtasks based on the user's description
+  //    - Ask it to create a task with subtasks based on the user's
+  // description
   //    - Specify the JSON format it should respond with
   //    - Include guidelines for creating good tasks and subtasks
   //
+  const systemPrompt = `
+    You are a task management assistant. Your job is to help users create tasks with subtasks.
+    Please follow these guidelines:
+    - Create a task with a title and description.
+    - Include subtasks with titles and descriptions.
+    - Respond in JSON format.
+    {
+      "title": "Task Title",
+      "description": "Task Description",
+      "subtasks": [
+        {
+          "title": "Subtask 1 Title",
+          "description": "Subtask 1 Description"
+        },
+        {
+          "title": "Subtask 2 Title",
+          "description": "Subtask 2 Description"
+        }
+      ]
+    }
+      guidelines:
+- The task should be short and clear.
+- Subtasks must be specific, actionable, and ordered logically.
+- Avoid vague terms like "do research" — instead be precise, e.g., "search online for top 5 tools."
+`;
+  
+
+
   // 3. Create a user prompt that includes the user's task description
   //    - Use the 'prompt' parameter passed to this function
   //
+  const userPrompt = ` ${prompt} `
   // 4. Call the OpenAI API using the openai client:
   //    - Use model: "gpt-3.5-turbo"
   //    - Include both system and user messages
   //    - Set temperature to 0.7 for balanced creativity
   //    - Set max_tokens to 1000
-  //
+  const completion = await openai.chat.completions.create({
+    model: "gpt-3.5-turbo",
+    messages: [
+      { role: "system", content: systemPrompt },
+      { role: "user", content: userPrompt }
+
+    ],
+    temperature: 0.7,
+    max_tokens: 1000
+  });
+
   // 5. Extract the response content from the API call
   //    - Access completion.choices[0]?.message?.content
   //    - Check if response exists, throw error if not
-  //
+  const responseContent = completion.choices[0]?.message?.content;
+  if (!responseContent) {
+    throw new Error("No response from AI");
+  }
+  
+
   // 6. Use the extractTaskFromAIResponse function to parse and validate the response
   //    - This function is already implemented for you
   //    - Pass the responseContent to it
+  const taskData = extractTaskFromAIResponse(responseContent);
   //
   // 7. Return the parsed task data
+ return taskData
   //
   // 8. Handle errors appropriately
   //    - Wrap everything in a try-catch block
   //    - Throw meaningful error messages
   //
 
-
-  throw new Error(
-    "TODO: Complete the generateTaskWithAI function - see instructions above"
-  );
+  } catch (error) {
+  throw new Error(`Failed to generate task with AI: ${error.message}`);
+}
 }