Passed Q1.

app.py

@@ -124,7 +124,12 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
+    count = 0
+    question_array = [2, 3, 4]  # Example question array for testing
     for item in questions_data:
+        count += 1
+        if count not in question_array:
+            continue
         task_id = item.get("task_id")
         question_text = item.get("question")
         if not task_id or question_text is None:
@@ -138,8 +143,6 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             print(f"Error running agent on task {task_id}: {e}")
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
 
-        break  # Test one question only first
-
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
@@ -195,7 +198,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner #17")
+    gr.Markdown("# Basic Agent Evaluation Runner #18")
     gr.Markdown(
         """
         **Instructions:**