diff --git a/src/documentation/how_tos/hot_to_implement_elo_evaluations.ipynb b/src/documentation/how_tos/hot_to_implement_elo_evaluations.ipynb
new file mode 100644
index 000000000..56c0b7ccc
--- /dev/null
+++ b/src/documentation/how_tos/hot_to_implement_elo_evaluations.ipynb
@@ -0,0 +1,23 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# How to implement elo evaluation runs\n",
+    "0. Run your tasks on the datasets you want to evaluate (see [here](./how_to_run_a_task_on_a_dataset.ipynb))\n",
+    "   - When evaluating multiple runs, all of them need the same data types \n",
+    "2. Initialize all necessary repositories for the `IncrementalEvaluator`, and an `IncrementalEvaluationLogic`.\n",
+    "3. Run the evaluator to evaluate all examples and create a single `EvaluationOverview`\n",
+    "4. (Optional) Save the evaluation id for later use"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}