diff --git a/packages/gooddata-eval/src/gooddata_eval/core/agentic/conversation.py b/packages/gooddata-eval/src/gooddata_eval/core/agentic/conversation.py
index a87338df3..f409593a9 100644
--- a/packages/gooddata-eval/src/gooddata_eval/core/agentic/conversation.py
+++ b/packages/gooddata-eval/src/gooddata_eval/core/agentic/conversation.py
@@ -70,6 +70,17 @@ class TurnResult(BaseModel):
     def skill_success(self) -> bool:
         return self.skill_routing and self.output_present and self.no_error
 
+    def detail(self) -> dict:
+        """The subset of this result reported in detail["turns"] for one conversation turn."""
+        return {
+            "turn_id": self.turn_id,
+            "expected_skill": self.expected_skill,
+            "skill_routing": self.skill_routing,
+            "output_present": self.output_present,
+            "output_correct": self.output_correct,
+            "activated_skills": self.activated_skills,
+        }
+
 
 def _resolve_refs(
     expected_output: dict | None,
@@ -430,17 +441,7 @@ def _conversation_detail(result: ConversationResult) -> dict:
     return {
         "full_skill_coverage": result.full_skill_coverage,
         "total_clarification_turns": result.total_clarification_turns,
-        "turns": [
-            {
-                "turn_id": tr.turn_id,
-                "expected_skill": tr.expected_skill,
-                "skill_routing": tr.skill_routing,
-                "output_present": tr.output_present,
-                "output_correct": tr.output_correct,
-                "activated_skills": tr.activated_skills,
-            }
-            for tr in result.turn_results
-        ],
+        "turns": [tr.detail() for tr in result.turn_results],
         "latency_breakdown": build_latency_breakdown(result.tool_call_events, result.reasoning_step_events),
     }