Ports #3975 to serverless (#4293)

* Port #3975 to serverless

* Add missing period

docs/en/serverless/ai-assistant/ai-assistant.mdx

@@ -254,7 +254,7 @@ You can continue a conversation from a contextual prompt by clicking **Start cha
 
 ### Add the AI Assistant connector to alerting workflows
 
-You can use the Observability AI Assistant connector to add AI-generated insights and custom actions to your alerting workflows.
+You can use the [Observability AI Assistant connector](((kibana-ref))/obs-ai-assistant-action-type.html) to add AI-generated insights and custom actions to your alerting workflows.
 To do this:
 
 1. <DocLink slug="/serverless/observability/create-manage-rules" text="Create (or edit) an alerting rule" /> and specify the conditions that must be met for the alert to fire.
@@ -290,7 +290,7 @@ The AI Assistant runs the tasks requested in the message and creates a conversat
 It might take a minute or two for the AI Assistant to process the message and create the conversation.
 
 Note that overly broad prompts may result in the request exceeding token limits.
-For more information, refer to <DocLink slug="/serverless/observability/ai-assistant" section="token-limits" />
+For more information, refer to <DocLink slug="/serverless/observability/ai-assistant" section="token-limits" />.
 Also, attempting to analyze several alerts in a single connector execution may cause you to exceed the function call limit.
 If this happens, modify the message specified in the connector configuration to avoid exceeding limits.