diff --git a/doxa-challenges/challenge-2/starter.ipynb b/doxa-challenges/challenge-2/starter.ipynb
index e227082..fc5991a 100644
--- a/doxa-challenges/challenge-2/starter.ipynb
+++ b/doxa-challenges/challenge-2/starter.ipynb
@@ -53,7 +53,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install numpy pandas matplotlib seaborn scikit-learn doxa-cli ipympl"
+    "%pip install numpy pandas matplotlib seaborn scikit-learn ipympl\n",
+    "%pip install -U doxa-cli"
    ]
   },
   {
@@ -112,11 +113,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "device = (\n",
-    "    \"cuda\"\n",
-    "    if torch.cuda.is_available()\n",
-    "    else \"cpu\"\n",
-    ")\n",
+    "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
     "print(f\"Using {device} device\")"
    ]
   },
@@ -142,7 +139,7 @@
    "source": [
     "# Load the data\n",
     "# !pip install ucimlrepo # uncomment this line if ucimlrepo is not installed\n",
-    "from ucimlrepo import fetch_ucirepo \n"
+    "from ucimlrepo import fetch_ucirepo"
    ]
   },
   {
@@ -151,10 +148,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# fetch dataset \n",
-    "wine_quality = fetch_ucirepo(id=186) \n",
-    "  \n",
-    "# data (as pandas dataframes) \n",
+    "# fetch dataset\n",
+    "wine_quality = fetch_ucirepo(id=186)\n",
+    "\n",
+    "# data (as pandas dataframes)\n",
     "df = wine_quality.data.features"
    ]
   },
@@ -174,7 +171,7 @@
    "source": [
     "# TODO: Print the first five rows of the data\n",
     "\n",
-    "# Hint: use the '.head()' method\n"
+    "# Hint: use the '.head()' method"
    ]
   },
   {
@@ -183,9 +180,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# TODO: Print the number of rows and columns in the dataset \n",
+    "# TODO: Print the number of rows and columns in the dataset\n",
     "\n",
-    "# Hint: use '.shape'\n"
+    "# Hint: use '.shape'"
    ]
   },
   {
@@ -196,7 +193,7 @@
    "source": [
     "# TODO: Print the summary statistics for the dataset\n",
     "\n",
-    "# Hint: use '.describe()'\n"
+    "# Hint: use '.describe()'"
    ]
   },
   {
@@ -221,10 +218,10 @@
    "source": [
     "# Important: do not change this cell!\n",
     "\n",
-    "# We split the data into X and y variables. X are the features and y is the target variable. we wand to predict. \n",
-    "# We are trying to predict the alcohol content given the other variables. \n",
-    "X = df.drop('alcohol', axis=1)\n",
-    "y = df['alcohol']\n",
+    "# We split the data into X and y variables. X are the features and y is the target variable. we wand to predict.\n",
+    "# We are trying to predict the alcohol content given the other variables.\n",
+    "X = df.drop(\"alcohol\", axis=1)\n",
+    "y = df[\"alcohol\"]\n",
     "\n",
     "# We done covert the Matrix X and vector y in numpy arrays.\n",
     "X = X.to_numpy()\n",
@@ -266,10 +263,8 @@
     "num_input_features, num_hidden_neurons = X_train.shape[1], 10\n",
     "model = nn.Sequential(\n",
     "    # TODO: add layers to our model\n",
-    "\n",
     "    # Note: remember that we are trying to predict a continuous variable.\n",
     "    # Our output layer should have only one neuron, and our input layer should be the number of columns in X.\n",
-    "\n",
     ")\n",
     "\n",
     "# Move model to GPU if available\n",
@@ -313,7 +308,7 @@
    "source": [
     "# TODO: replace 'None' with your loss function.\n",
     "\n",
-    "# Hint: we are trying to predict a continuous variable.\n"
+    "# Hint: we are trying to predict a continuous variable."
    ]
   },
   {
@@ -346,7 +341,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "#Keep track of losses\n",
+    "# Keep track of losses\n",
     "plotlosses = PlotLosses()\n",
     "\n",
     "# Convert our training data to tensors\n",
@@ -400,12 +395,12 @@
     "with torch.no_grad():\n",
     "    # Print the loss on the training data\n",
     "    y_pred_train = model(torch.from_numpy(X_train).float().to(device)).numpy()\n",
-    "    mse_loss_train = np.mean((y_pred_train - y_train)**2) # Mean Square Error loss\n",
+    "    mse_loss_train = np.mean((y_pred_train - y_train) ** 2)  # Mean Square Error loss\n",
     "    print(f\"Train MSE loss: {mse_loss_train:.2f}\")\n",
-    "    \n",
+    "\n",
     "    # Print the loss on the test data\n",
     "    y_pred_test = model(torch.from_numpy(X_test).float().to(device)).numpy()\n",
-    "    mse_loss_test = np.mean((y_pred_test - y_test)**2) # Mean Square Error loss\n",
+    "    mse_loss_test = np.mean((y_pred_test - y_test) ** 2)  # Mean Square Error loss\n",
     "\n",
     "    print(f\"Test MSE loss: {mse_loss_test:.2f}\")"
    ]
@@ -425,11 +420,11 @@
    "source": [
     "# Pass our data through our neural network\n",
     "model.eval()\n",
-    "with torch.no_grad():    \n",
+    "with torch.no_grad():\n",
     "    # Print the loss on the test data\n",
     "    predictions = model(torch.from_numpy(X_test).float().to(device)).numpy().squeeze()\n",
     "\n",
-    "assert predictions.shape == (1300,) \n",
+    "assert predictions.shape == (1300,)\n",
     "\n",
     "# Take a look at the first 20 predictions\n",
     "predictions[:20]"
@@ -441,17 +436,24 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Prepare our submission package\n",
     "os.makedirs(\"submission\", exist_ok=True)\n",
     "\n",
     "with open(\"submission/y.txt\", \"w\") as f:\n",
     "    f.writelines([f\"{prediction}\\n\" for prediction in predictions])\n",
     "\n",
     "with open(\"submission/doxa.yaml\", \"w\") as f:\n",
-    "    f.write(\"competition: epl\\nenvironment: cpu\\nlanguage: python\\nentrypoint: run.py\")\n",
+    "    f.write(\n",
+    "        \"competition: uclais-2023-2\\nenvironment: cpu\\nlanguage: python\\nentrypoint: run.py\"\n",
+    "    )\n",
     "\n",
     "with open(\"submission/run.py\", \"w\") as f:\n",
-    "    f.write(\"with open('y.txt', 'r') as f: print(f.read().strip())\")"
+    "    f.write(\n",
+    "        \"\"\"import os\n",
+    "\n",
+    "with open('y.txt', 'r') as f:\n",
+    "    with open(os.environ[\"DOXA_STREAMS\"] + \"/out\", \"w\") as g:\n",
+    "        g.write(f.read().strip())\"\"\"\n",
+    "    )"
    ]
   },
   {