diff --git a/docs/ai-pod-docs/openshift-readme.md b/docs/ai-pod-docs/openshift-readme.md
index 0ae54a59..f874d480 100644
--- a/docs/ai-pod-docs/openshift-readme.md
+++ b/docs/ai-pod-docs/openshift-readme.md
@@ -156,6 +156,19 @@ flowchart TB
 > This installer is qualified for OpenShift 4.21. Setting another version in
 > the configuration does not add support for that OpenShift release.
 
+### Infrastructure references
+
+Provision the OpenShift cluster and Cisco UCS hardware before running the AI
+POD installer:
+
+- [OpenShift installation and configuration](https://www.cisco.com/c/en/us/td/docs/unified_computing/ucs/UCS_CVDs/flexpod_aipod_training_manual.html#OpenShiftInstallationandConfiguration)
+- [Cisco UCS C845A M8 Rack Server](https://www.cisco.com/c/en/us/products/collateral/servers-unified-computing/ucs-c-series-rack-servers/ucs-c845a-m8-rack-server-ds.html)
+
+The OpenShift reference includes an infrastructure example based on different
+GPU hardware. It does not replace the AI POD requirements below. The qualified
+AI POD configuration uses a Cisco UCS C845A M8 with two NVIDIA RTX PRO 6000
+Blackwell GPUs.
+
 ### Minimum deployment requirements
 
 The qualified minimum deployment uses one shared AI-tier worker node for CPU