diff --git a/site/en/gemini-api/tutorials/anomaly_detection.ipynb b/site/en/gemini-api/tutorials/anomaly_detection.ipynb
index 348e61198..09b77ee64 100644
--- a/site/en/gemini-api/tutorials/anomaly_detection.ipynb
+++ b/site/en/gemini-api/tutorials/anomaly_detection.ipynb
@@ -68,7 +68,7 @@
         "\n",
         "This tutorial demonstrates how to use the embeddings from the Gemini API to detect potential outliers in your dataset. You will visualize a subset of the 20 Newsgroup dataset using [t-SNE](https://scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html){:.external} and detect outliers outside a particular radius of the central point of each categorical cluster.\n",
         "\n",
-        "For more information on getting started with embeddings generated from the Gemini API, check out the [Python quickstart](../tutorials/python_quickstart.ipynb#use_embeddings).\n",
+        "For more information on getting started with embeddings generated from the Gemini API, check out the [Python quickstart](https://ai.google.dev/tutorials/python_quickstart#use_embeddings).\n",
         "\n",
         "## Prerequisites\n",
         "\n",
@@ -162,7 +162,7 @@
       "source": [
         "Key Point: Next, you will choose a model. Any embedding model will work for this tutorial, but for real applications it's important to choose a specific model and stick with it. The outputs of different models are not compatible with each other.\n",
         "\n",
-        "**Note**: At this time, the Gemini API is [only available in certain regions](https://developers.generativeai.google/available_regions)."
+        "**Note**: At this time, the Gemini API is [only available in certain regions](https://ai.google.dev/available_regions)."
       ]
     },
     {
@@ -2934,7 +2934,7 @@
         "\n",
         "You've now created an anomaly detector using embeddings! Try using your own textual data to visualize them as embeddings, and choose some bound such that you can detect outliers. You can perform dimensionality reduction in order to complete the visualization step. Note that t-SNE is good at clustering inputs, but can take a longer time to converge or might get stuck at local minima. If you run into this issue, another technique you could consider are [principal components analysis (PCA)](https://en.wikipedia.org/wiki/Principal_component_analysis){:.external}.\n",
         "\n",
-        "To learn how to use other services in the Gemini API, visit the [Python quickstart](../tutorials/python_quickstart.ipynb).\n",
+        "To learn how to use other services in the Gemini API, visit the [Python quickstart](https://ai.google.dev/tutorials/python_quickstart).\n",
         "\n",
         "To learn more about how you can use the embeddings, check out the [examples](../examples?keywords=embed) available. To learn how to create them from scratch, see TensorFlow's [Word Embeddings](https://www.tensorflow.org/text/guide/word_embeddings){:.external} tutorial."
       ]