diff --git a/haiku_rag_slim/haiku/rag/graph/common/prompts.py b/haiku_rag_slim/haiku/rag/graph/common/prompts.py
index 29eb922f..ed8d49c2 100644
--- a/haiku_rag_slim/haiku/rag/graph/common/prompts.py
+++ b/haiku_rag_slim/haiku/rag/graph/common/prompts.py
@@ -50,8 +50,13 @@ Each result includes:
 - Type: content type like paragraph, table, code, list_item (when available)
 - Content: the actual text
 
-IMPORTANT: cited_chunks must be a list of plain strings containing only the UUIDs.
-Use the EXACT, COMPLETE chunk ID. Do NOT use objects or truncate IDs.
+Output format:
+- query: Echo the question you are answering
+- answer: Your concise answer based on the retrieved content
+- cited_chunks: List of plain strings containing only the chunk UUIDs (not objects)
+- confidence: A score from 0.0 to 1.0 indicating answer confidence
+
+IMPORTANT: Use the EXACT, COMPLETE chunk ID (full UUID). Do NOT truncate IDs.
 
 Guidelines:
 - Base answers strictly on retrieved content - do not use external knowledge.
diff --git a/haiku_rag_slim/haiku/rag/graph/deep_qa/prompts.py b/haiku_rag_slim/haiku/rag/graph/deep_qa/prompts.py
index 3d638358..9dc46615 100644
--- a/haiku_rag_slim/haiku/rag/graph/deep_qa/prompts.py
+++ b/haiku_rag_slim/haiku/rag/graph/deep_qa/prompts.py
@@ -9,8 +9,10 @@ Task:
 - Be clear, accurate, and well-structured
 
 Output format:
+- query: Echo the original question being answered
 - answer: The complete answer to the original question (2-4 paragraphs)
 - cited_chunks: List of plain strings containing chunk IDs (UUIDs only, not objects)
+- confidence: A score from 0.0 to 1.0 indicating answer confidence
 
 Guidelines:
 - Start directly with the answer - no preamble like "Based on the research..."