diff --git a/template.yaml b/template.yaml
index dec834b..00adeca 100644
--- a/template.yaml
+++ b/template.yaml
@@ -247,8 +247,7 @@ objects:
           * Upon successful cluster creation, inform the user and provide the **cluster ID**.
 
           **Mandatory Pre-Flight Checks for Cluster Creation**
-          * **Unsupported Network Configuration:** Before attempting to create a cluster, you **must first check** if the user's request includes instructions for unsupported network configurations, such as **static networking**, **static IP addresses**, or **node-level network settings** (like MAC addresses, gateways, or DNS servers).
-          * **If an unsupported configuration is detected, you must refuse the entire request.** Do not proceed with cluster creation. Your response must state that you don't support the requested static networking configuration and then instruct the user to use the assisted-installer web-based wizard instead.
+          * **Unsupported Network Configuration:** If the user's request includes instructions for unsupported network configurations, such as **static networking**, **static IP addresses**, or **node-level network settings** (like MAC addresses, gateways, or or DNS servers), you must refuse the entire request.** Do not proceed with cluster creation. Your response must state that you don't support the requested static networking configuration and then instruct the user to use the assisted-installer web-based wizard instead.
           * **Important Distinction:** Do not confuse unsupported static networking with setting API and Ingress VIPs. VIPs are a different concept and are supported for multi-node clusters with user-managed networking disabled.
 
       2.  **Infrastructure Setup / ISO Download:**
@@ -258,7 +257,11 @@ objects:
 
       3.  **Host Discovery and Configuration:**
           * Once the Discovery ISO is generated, the user needs to boot hosts with it.
-          * After hosts are discovered and appear in the cluster's hosts list, offer to help **assign roles to the hosts** (e.g., master, worker).
+          * When a user indicates that hosts have been booted, first check for discovered hosts for that cluster and the cluster status.
+          * After hosts are discovered and appear in the hosts list, present the full list of discovered hosts to the user.
+          * Proactively offer the next steps based on the cluster type:
+              * **For a multi-node cluster:** Inform the user that roles can be automatically assigned or they can manually assign them. Offer to help with **manual role assignment** to a specific host (e.g., master, worker).
+              * **For a Single Node OpenShift (SNO) cluster:** Inform the user that the host is automatically assigned the `master` role and no further manual role assignment is needed. Propose the next logical step, such as initiating the installation.
           * If the user wants to monitor host-specific issues, offer to retrieve **host events**.
           * Different cluster types and host roles have different hardware requirements:
             * For a multi-node cluster:
diff --git a/test/evals/eval_data.yaml b/test/evals/eval_data.yaml
index c32c835..5254a30 100644
--- a/test/evals/eval_data.yaml
+++ b/test/evals/eval_data.yaml
@@ -117,6 +117,14 @@
             arguments:
               cluster_id: "[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}"
       expected_keywords: ["Discovery ISO"]
+    - eval_id: host_booted_but_not_discovered
+      eval_query: I booted the hosts
+      eval_types: [tool_eval, response_eval:accuracy]
+      expected_tool_calls:
+        - - tool_name: cluster_info
+            arguments:
+              cluster_id: "[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}"
+      expected_response: "hosts hasn't been discovered yet."
 
 - conversation_group: list_clusters_conv
   conversation:
@@ -131,13 +139,12 @@
   conversation:
     - eval_id: cluster_info_tool_call
       eval_query: Give me details about cluster named 'abc123abc'
+      description: Test handling for non-existent cluster name
       eval_types: [tool_eval, response_eval:accuracy]
+      expected_response: Retrieval failed for cluster 'abc123abc' because the resource was not found.
       expected_tool_calls:
-        # It should list the clusters to try to match up the name
         - - tool_name: list_clusters
             arguments: {}
-      description: Test handling for non-existent cluster ID/Name
-      expected_response: Retrieval failed for cluster 'abc123abc' because the resource was not found.
 
 - conversation_group: error_handling_conv
   description: Validate graceful handling of invalid SSH key format