diff --git a/src/intelligence_layer/evaluation/data_storage/evaluation_repository.py b/src/intelligence_layer/evaluation/data_storage/evaluation_repository.py
index f43c819cf..08b59b8bc 100644
--- a/src/intelligence_layer/evaluation/data_storage/evaluation_repository.py
+++ b/src/intelligence_layer/evaluation/data_storage/evaluation_repository.py
@@ -369,7 +369,7 @@ def store_example_evaluation(
     ) -> None:
         if isinstance(evaluation.result, RecordDataSequence):
             for record in evaluation.result.records:
-                self._client.add_record(evaluation.example_id, record)
+                self._client.add_record(evaluation.eval_id, record)
         raise TypeError(
             "ArgillaEvaluationRepository does not support storing non-RecordDataSequence evaluations."
         )
diff --git a/src/intelligence_layer/use_cases/classify/classify.py b/src/intelligence_layer/use_cases/classify/classify.py
index 44ca4e44e..ae3dcc1df 100644
--- a/src/intelligence_layer/use_cases/classify/classify.py
+++ b/src/intelligence_layer/use_cases/classify/classify.py
@@ -97,7 +97,7 @@ def do_evaluate(
     ) -> SingleLabelClassifyEvaluation:
         assert len(output) == 1
         sorted_classes = sorted(
-            output[0].scores.items(), key=lambda item: item[1], reverse=True  # TODO
+            output[0].scores.items(), key=lambda item: item[1], reverse=True
         )
         if sorted_classes[0][0] in example.expected_output:
             correct = True