diff --git a/rule-engine/rule-engine-components/src/main/java/org/thingsboard/rule/engine/ai/TbAiNode.java b/rule-engine/rule-engine-components/src/main/java/org/thingsboard/rule/engine/ai/TbAiNode.java
index 93c2cafaae..6c4815308a 100644
--- a/rule-engine/rule-engine-components/src/main/java/org/thingsboard/rule/engine/ai/TbAiNode.java
+++ b/rule-engine/rule-engine-components/src/main/java/org/thingsboard/rule/engine/ai/TbAiNode.java
@@ -52,9 +52,20 @@ import static org.thingsboard.server.dao.service.ConstraintValidator.validateFie
@RuleNode(
type = ComponentType.EXTERNAL,
- name = "AI",
- nodeDescription = "Interact with AI",
- nodeDetails = "This node makes requests to AI based on a prompt and a input message and returns a response in a form of output message",
+ name = "AI request",
+ nodeDescription = "Sends a request to an AI model using system and user prompts. Supports JSON mode.",
+ nodeDetails = """
+ Interact with large language models (LLMs) by sending dynamic requests from your rule chain.
+ You can select a specific AI model and define its behavior using a system prompt (optional context or role) and a user prompt (the main task).
+ Both prompts can be populated with data and metadata from the incoming message using patterns.
+ For example, the $[*] and ${*} patterns allow you to access the all message body and all metadata, respectively.
+
+ After sending the request, the node waits for a response within a configured timeout.
+ You can specify the desired response format as Text, JSON, or provide a specific JSON Schema to structure the output.
+ The AI-generated content is forwarded as the body of the outgoing message; the originator, message type, and metadata from the incoming message remain unchanged.
+
+ Output connections: Success, Failure.
+ """,
configClazz = TbAiNodeConfiguration.class,
ruleChainTypes = RuleChainType.CORE
)