diff --git a/modules/chapter1/images/ServingRuntimes.png b/modules/chapter1/images/ServingRuntimes.png
new file mode 100644
index 0000000..0c250fe
Binary files /dev/null and b/modules/chapter1/images/ServingRuntimes.png differ
diff --git a/modules/chapter1/images/add-custom-model-server.png b/modules/chapter1/images/add-custom-model-server.png
new file mode 100644
index 0000000..8f07f9c
Binary files /dev/null and b/modules/chapter1/images/add-custom-model-server.png differ
diff --git a/modules/chapter1/images/add_serving_runtime.png b/modules/chapter1/images/add_serving_runtime.png
new file mode 100644
index 0000000..1b311e6
Binary files /dev/null and b/modules/chapter1/images/add_serving_runtime.png differ
diff --git a/modules/chapter1/images/custom-model-server-form.png b/modules/chapter1/images/custom-model-server-form.png
new file mode 100644
index 0000000..9c27bef
Binary files /dev/null and b/modules/chapter1/images/custom-model-server-form.png differ
diff --git a/modules/chapter1/images/custom-runtime.png b/modules/chapter1/images/custom-runtime.png
new file mode 100644
index 0000000..0acfb26
Binary files /dev/null and b/modules/chapter1/images/custom-runtime.png differ
diff --git a/modules/chapter1/images/iris-custom-deploy-model-form.png b/modules/chapter1/images/iris-custom-deploy-model-form.png
new file mode 100644
index 0000000..2c89641
Binary files /dev/null and b/modules/chapter1/images/iris-custom-deploy-model-form.png differ
diff --git a/modules/chapter1/images/iris-custom-deploy-model.png b/modules/chapter1/images/iris-custom-deploy-model.png
new file mode 100644
index 0000000..4a54bbc
Binary files /dev/null and b/modules/chapter1/images/iris-custom-deploy-model.png differ
diff --git a/modules/chapter1/images/runtimes-list.png b/modules/chapter1/images/runtimes-list.png
new file mode 100644
index 0000000..f27d4e2
Binary files /dev/null and b/modules/chapter1/images/runtimes-list.png differ
diff --git a/modules/chapter1/images/triton-server-running.png b/modules/chapter1/images/triton-server-running.png
new file mode 100644
index 0000000..caa07f7
Binary files /dev/null and b/modules/chapter1/images/triton-server-running.png differ
diff --git a/modules/chapter1/pages/section3.adoc b/modules/chapter1/pages/section3.adoc
index 17a0eda..d2a5fa0 100644
--- a/modules/chapter1/pages/section3.adoc
+++ b/modules/chapter1/pages/section3.adoc
@@ -1,4 +1,192 @@
-= Section 3
+= Section 3: Creating a Custom Model Serving Runtime
 
-This is _Section 3_ of _Chapter 1_ in the *hello* quick course....
+A model-serving runtime provides integration with a specified model server and the model frameworks that it supports. By default, Red Hat OpenShift Data Science includes the OpenVINO Model Server runtime. However, if this runtime doesn’t meet your needs (it doesn’t support a particular model framework, for example), you might want to add your own, custom runtimes.
+
+As an administrator, you can use the OpenShift Data Science interface to add and enable custom model-serving runtimes. You can then choose from your enabled runtimes when you create a new model server.
+
+== Prerequisite
+
+In order to run this exercise, be sure to have handy the model we created in the previous section, that is:
+
+- An s3 bucket with a model in format **onnx**
+- A Data Science project with the name **iris-project**
+- A data connection to S3 with the name **iris-data-connection**
+
+This exercise will guide you through the broad steps necessary to deploy a custom Serving Runtime in order to serve a model using the Triton Runtime (NVIDIA Triton Inference Server).
+
+While RHODS supports your ability to add your own runtime, it does not support the runtimes themselves. Therefore, it is up to you to configure, adjust and maintain your custom runtimes.
+
+== Adding The Custom Runtime
+
+. Log in to RHODS with a user who is part of the RHODS admin group
+
+. Navigate to the Settings menu, then Serving Runtimes
++
+image::ServingRuntimes.png[Serving Runtimes]
+
+. Click on the Add Serving Runtime button:
++
+image::add_serving_runtime.png[Add Serving Runtime]
+
+. Click on Start from scratch and in the window that opens up, paste the following YAML:
++
+```yaml
+apiVersion: serving.kserve.io/v1alpha1
+kind: ServingRuntime
+metadata:
+  name: triton-23.05-20230804
+  labels:
+    name: triton-23.05-20230804
+  annotations:
+    maxLoadingConcurrency: "2"
+    openshift.io/display-name: "Triton runtime 23.05"
+spec:
+  supportedModelFormats:
+    - name: keras
+      version: "2" 
+      autoSelect: true
+    - name: onnx
+      version: "1" 
+      autoSelect: true
+    - name: pytorch
+      version: "1" 
+      autoSelect: true
+    - name: tensorflow
+      version: "1" 
+      autoSelect: true
+    - name: tensorflow
+      version: "2" 
+      autoSelect: true
+    - name: tensorrt
+      version: "7" 
+      autoSelect: true
+
+  protocolVersions:
+    - grpc-v2
+  multiModel: true
+
+  grpcEndpoint: "port:8085"
+  grpcDataEndpoint: "port:8001"
+
+  volumes:
+    - name: shm
+      emptyDir:
+        medium: Memory
+        sizeLimit: 2Gi
+  containers:
+    - name: triton
+      image: nvcr.io/nvidia/tritonserver:23.05-py3
+      command: [/bin/sh]
+      args:
+        - -c
+        - 'mkdir -p /models/_triton_models;
+          chmod 777 /models/_triton_models;
+          exec tritonserver
+          "--model-repository=/models/_triton_models"
+          "--model-control-mode=explicit"
+          "--strict-model-config=false"
+          "--strict-readiness=false"
+          "--allow-http=true"
+          "--allow-sagemaker=false"
+          '
+      volumeMounts:
+        - name: shm
+          mountPath: /dev/shm
+      resources:
+        requests:
+          cpu: 500m
+          memory: 1Gi
+        limits:
+          cpu: "5"
+          memory: 1Gi
+      livenessProbe:
+        # the server is listening only on 127.0.0.1, so an httpGet probe sent
+        # from the kublet running on the node cannot connect to the server
+        # (not even with the Host header or host field)
+        # exec a curl call to have the request originate from localhost in the
+        # container
+        exec:
+          command:
+            - curl
+            - --fail
+            - --silent
+            - --show-error
+            - --max-time
+            - "9"
+            - http://localhost:8000/v2/health/live
+        initialDelaySeconds: 5
+        periodSeconds: 30
+        timeoutSeconds: 10
+  builtInAdapter:
+    serverType: triton
+    runtimeManagementPort: 8001
+    memBufferBytes: 134217728
+    modelLoadingTimeoutMillis: 90000
+```
+
+. After clicking the **Add** button at the bottom of the input area, we are able to see the new Runtime in the list. We can re-order the list as needed (the order chosen here is the order in which the users will see these choices)
++
+image::runtimes-list.png[Runtimes List]
+
+== Creating The Model Server
+
+. Using the **iris-project** created in the previous section, scroll to the **Models and model servers** section, and select the **Add server** button
++
+image::add-custom-model-server.png[Add server]
+
+. Fill up the form as in the following example, notice how **Triton runtime 23.05** is one of the available options for the **Serving runtime** dropdown.
++
+image:custom-model-server-form.png[Add model server form]
+
+. After clicking the **Add** button at the bottom of the form, we are able to see our **iris-custom-server** model server, created with the **Triton runtime 23.05** serving runtime.
++
+image::custom-runtime.png[Iris custom server]
+
+== Deploy The Model
+
+. Use the **Deploy Model** button at the right of the row with the **iris-custom-server** model server
++
+image::iris-custom-deploy-model.png[Deploy Model]
+
+. Fill up the **Deploy Model** form as in the following example:
++
+image::iris-custom-deploy-model-form.png[Deploy model form]
++
+[IMPORTANT]
+====
+Notice the model name, in this exercise we are naming it **iris-custom-model**, _we can't use the **iris-model** name anymore_.
+You can be creative and name it differently, just mind your selection when running the inference service with the APIs.
+====
+
+. After clicking the **Deploy** button at the bottom of the form, we see the model added to our **Model Server** row, wait for the green checkmark to appear.
++
+image::triton-server-running.png[Triton server running]
+
+== Test The Model With CURL
+
+Now that the model is ready to use, we can make an inference using the REST API
+
+. Assign the route to an environment variable in your local machine, so that we can use it in our curl commands
++
+```shell
+export IRIS_ROUTE=https://$(oc get routes -n iris-project | grep iris-custom-model | awk '{print $2}')
+```
+
+. Assign an authentication token to an environment variable in your local machine
++
+```shell
+export TOKEN=$(oc whoami -t)
+```
+
+. Request an inference with the REST API
++
+```shell
+curl -H "Authorization: Bearer $TOKEN" $IRIS_ROUTE/v2/models/iris-custom-model/infer -X POST --data '{"inputs" : [{"name" : "X","shape" : [ 1, 4 ],"datatype" : "FP32","data" : [ 3, 4, 3, 2 ]}]}'
+```
+
+. The result received from the inference service looks like the following:
++
+```json
+{"model_name":"iris-custom-model__isvc-9cc7f4ebab","model_version":"1","outputs":[{"name":"label","datatype":"INT64","shape":[1,1],"data":[1]},{"name":"scores","datatype":"FP32","shape":[1,3],"data":[4.851966,3.1275778,3.4580243]}]}
+```