diff --git a/people_data_enrichment/run_eval.py b/people_data_enrichment/run_eval.py
index d29db5c..1136f84 100644
--- a/people_data_enrichment/run_eval.py
+++ b/people_data_enrichment/run_eval.py
@@ -62,8 +62,8 @@ EVALUATION_PROMPT = f"""You are an evaluator tasked with assessing the accuracy
 
 
 def evaluate_agent(outputs: dict, reference_outputs: dict):
-    if "info" not in outputs or not isinstance(outputs["info"], dict):
-        return 0.0
+    if "info" not in outputs:
+        raise ValueError("Agent output must contain 'info' key")
 
     class Score(BaseModel):
         """Evaluate the agent's output against the expected output."""
diff --git a/public_company_data_enrichment/run_eval.py b/public_company_data_enrichment/run_eval.py
index a6f2220..ba5765e 100644
--- a/public_company_data_enrichment/run_eval.py
+++ b/public_company_data_enrichment/run_eval.py
@@ -35,8 +35,8 @@ EVALUATION_PROMPT = f"""You are an evaluator tasked with assessing the accuracy
 
 
 def evaluate_agent(outputs: dict, reference_outputs: dict):
-    if "info" not in outputs or not isinstance(outputs["info"], dict):
-        return 0.0
+    if "info" not in outputs:
+        raise ValueError("Agent output must contain 'info' key")
 
     class Score(BaseModel):
         """Evaluate the agent's output against the expected output."""
diff --git a/startup_data_enrichment/run_eval.py b/startup_data_enrichment/run_eval.py
index e6e26b4..843fd0d 100644
--- a/startup_data_enrichment/run_eval.py
+++ b/startup_data_enrichment/run_eval.py
@@ -41,8 +41,8 @@ EVALUATION_PROMPT = f"""You are an evaluator tasked with assessing the accuracy
 
 
 def evaluate_agent(outputs: dict, reference_outputs: dict):
-    if "info" not in outputs or not isinstance(outputs["info"], dict):
-        return 0.0
+    if "info" not in outputs:
+        raise ValueError("Agent output must contain 'info' key")
 
     class Score(BaseModel):
         """Evaluate the agent's output against the expected output."""