On the “Workflows + agents” page here Workflows and agents - Docs by LangChain
There seems to be an issue the Prompt Chaining example
The “if…else” statement below uses the “else” block to indicate that there was no punchline detected in the joke
Meanwhile, the if block is what actually runs if the joke fails with no punchline and is then improved
The else block runs if the joke actually passed the first time:
if "improved_joke" in state:
print("Improved joke:")
print(state["improved_joke"])
print("\n--- --- ---\n")
print("Final joke:")
print(state["final_joke"])
else:
print("Joke failed quality gate - no punchline detected!")