Updated llm_as_a_judge.py (#1055)

zaidrj · web-flow · commit a9757de76736 · 2025-07-11T11:05:38.000+09:00
Updated the evaluator agent’s instructions in llm_as_a_judge.py to
prevent infinite evaluation loops. The agent is now instructed to
provide a final evaluation after 5 attempts, allowing approval if the
story outline is good enough, even if it is not perfect.
diff --git a/examples/agent_patterns/llm_as_a_judge.py b/examples/agent_patterns/llm_as_a_judge.py
@@ -32,7 +32,7 @@ class EvaluationFeedback:
     instructions=(
         "You evaluate a story outline and decide if it's good enough."
         "If it's not good enough, you provide feedback on what needs to be improved."
-        "Never give it a pass on the first try."
+        "Never give it a pass on the first try. after 5 attempts, you can give it a pass if story outline is good enough - do not go for perfection"
     ),
     output_type=EvaluationFeedback,
 )

Original file line number	Diff line number	Diff line change
`@@ -32,7 +32,7 @@ class EvaluationFeedback:`
`32`	`32`	`instructions=(`
`33`	`33`	`"You evaluate a story outline and decide if it's good enough."`
`34`	`34`	`"If it's not good enough, you provide feedback on what needs to be improved."`
`35`		`- "Never give it a pass on the first try."`
	`35`	`+ "Never give it a pass on the first try. after 5 attempts, you can give it a pass if story outline is good enough - do not go for perfection"`
`36`	`36`	`),`
`37`	`37`	`output_type=EvaluationFeedback,`
`38`	`38`	`)`