From 57b00526f8920ec93db1235df07c79a3f97edd82 Mon Sep 17 00:00:00 2001 From: Roman Rizzi Date: Fri, 27 Jun 2025 16:59:55 -0300 Subject: [PATCH] FIX: Clarify spam response expectations. (#1470) --- lib/personas/spam_detector.rb | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/lib/personas/spam_detector.rb b/lib/personas/spam_detector.rb index abf09d38..85f782a5 100644 --- a/lib/personas/spam_detector.rb +++ b/lib/personas/spam_detector.rb @@ -44,13 +44,13 @@ module DiscourseAi - Site description: {site_description} - Site top 10 categories: {top_categories} - Format your response as a JSON object with a one key named "spam", which indicates if a post is spam or legitimate. + Format your response as a JSON object with a one key named "spam", which is a boolean that indicates if a post is spam or legitimate. Your output should be in the following format: - {"spam": "xx"} + {"spam": xx} - Where "xx" is true if the post is spam, or false if it's legitimate. + Where xx is true if the post is spam, or false if it's legitimate. PROMPT end