I don't understand. If you're already building the rules, why have a clanker summarize and guess why the result happened when you can display the rules that passed/failed?
I don't understand. If you're already building the rules, why have a clanker summarize and guess why the result happened when you can display the rules that passed/failed?
Fair question, and you can do exactly that( response_mode:"verdict_only") makes no LLM call
[flagged]
[flagged]