diff --git a/src/backend/agents/base.py b/src/backend/agents/base.py
index a9c99f2..e3aa1d4 100644
--- a/src/backend/agents/base.py
+++ b/src/backend/agents/base.py
@@ -358,8 +358,9 @@ class Agent(BaseModel, ABC):
                         size=user.file_watcher.collection.count()
                     )
 
+                    entries += len(rag_metadata.documents)
                     rag_message.metadata.rag_results.append(rag_metadata)
-                    rag_message.content = f"Results from {rag.name} RAG: {len(chroma_results['documents'])} results."
+                    rag_message.content = f"Results from {rag.name} RAG: {len(rag_metadata.documents)} results."
                     yield rag_message
 
             rag_message.content = (
@@ -377,7 +378,7 @@ class Agent(BaseModel, ABC):
             return
 
     async def generate(
-        self, llm: Any, model: str, user_message: ChatMessageUser, user_id: str, temperature=0.7
+        self, llm: Any, model: str, user_message: ChatMessageUser, user: Candidate, temperature=0.7
     ) -> AsyncGenerator[ChatMessage | ChatMessageBase, None]:
         logger.info(f"{self.agent_type} - {inspect.stack()[0].function}")
 
diff --git a/src/backend/agents/candidate_chat.py b/src/backend/agents/candidate_chat.py
index 072a8f5..c165fe8 100644
--- a/src/backend/agents/candidate_chat.py
+++ b/src/backend/agents/candidate_chat.py
@@ -7,11 +7,10 @@ from .base import Agent, agent_registry
 from logger import logger
 
 from .registry import agent_registry
-from models import ( ChatQuery, ChatMessage, Tunables, ChatStatusType)
+from models import ( ChatQuery, ChatMessage, Tunables, ChatStatusType, ChatMessageUser, Candidate)
+
 
 system_message = f"""
-Launched on {datetime.now().isoformat()}.
-
 When answering queries, follow these steps:
 
 - First analyze the query to determine if real-time information from the tools might be helpful
@@ -57,31 +56,18 @@ class CandidateChat(Agent):
 
     system_prompt: str = system_message
 
-#     async def prepare_message(self, message: Message) -> AsyncGenerator[Message, None]:
-#         logger.info(f"{self.agent_type} - {inspect.stack()[0].function}")
-#         if not self.context:
-#             raise ValueError("Context is not set for this agent.")
-
-#         async for message in super().prepare_message(message):
-#             if message.status != "done":
-#                 yield message
-
-#         if message.preamble:
-#             excluded = {}
-#             preamble_types = [
-#                 f"<|{p}|>" for p in message.preamble.keys() if p not in excluded
-#             ]
-#             preamble_types_AND = " and ".join(preamble_types)
-#             preamble_types_OR = " or ".join(preamble_types)
-#             message.preamble[
-#                 "rules"
-#             ] = f"""\
-# - Answer the question based on the information provided in the {preamble_types_AND} sections by incorporate it seamlessly and refer to it using natural language instead of mentioning {preamble_types_OR} or quoting it directly.
-# - If there is no information in these sections, answer based on your knowledge, or use any available tools.
-# - Avoid phrases like 'According to the {preamble_types[0]}' or similar references to the {preamble_types_OR}.
-# """
-#         message.preamble["question"] = "Respond to:"
+    async def generate(
+        self, llm: Any, model: str, user_message: ChatMessageUser, user: Candidate, temperature=0.7
+    ):
+        self.system_prompt = """
+You are a helpful assistant designed to answer questions about {candidate.full_name}, their resumes, and related topics. You can also generate images based on user requests.        
 
+{system_message}
+"""
+        async for message in super().generate(llm, model, user_message, user, temperature):
+            yield message
+    
 
 # Register the base agent
 agent_registry.register(CandidateChat._agent_type, CandidateChat)
+
diff --git a/src/backend/main.py b/src/backend/main.py
index 5439c4a..30c7d3a 100644
--- a/src/backend/main.py
+++ b/src/backend/main.py
@@ -1994,7 +1994,7 @@ async def post_chat_session_message_stream(
                     llm=llm_manager.get_llm(),
                     model=defines.model,
                     user_message=user_message,
-                    user_id=current_user.id,
+                    user=current_user,
                 ):
                     # Store reference to the complete AI message
                     if generated_message.status == ChatStatusType.DONE: