diff --git a/config/locales/server.en.yml b/config/locales/server.en.yml
index 3e4c1064..eaa0bfcc 100644
--- a/config/locales/server.en.yml
+++ b/config/locales/server.en.yml
@@ -3,6 +3,7 @@ en:
     ai:
       flag_types:
         review: "Add post to review queue"
+        review_hide: "Add post to review queue and hide post"
         spam: "Flag as spam and hide post"
         spam_silence: "Flag as spam, hide post and silence user"
     scriptables:
diff --git a/lib/automation.rb b/lib/automation.rb
index 06a36c9a..e43bcbc5 100644
--- a/lib/automation.rb
+++ b/lib/automation.rb
@@ -5,6 +5,10 @@ module DiscourseAi
     def self.flag_types
       [
         { id: "review", translated_name: I18n.t("discourse_automation.ai.flag_types.review") },
+        {
+          id: "review_hide",
+          translated_name: I18n.t("discourse_automation.ai.flag_types.review_hide"),
+        },
         { id: "spam", translated_name: I18n.t("discourse_automation.ai.flag_types.spam") },
         {
           id: "spam_silence",
diff --git a/lib/automation/llm_triage.rb b/lib/automation/llm_triage.rb
index 640e7046..20ab9ae4 100644
--- a/lib/automation/llm_triage.rb
+++ b/lib/automation/llm_triage.rb
@@ -148,6 +148,11 @@ module DiscourseAi
                 reason: score_reason,
                 force_review: true,
               )
+
+              # We cannot do this through the PostActionCreator because hiding a post is reserved for auto action flags.
+              # Those flags are off_topic, inappropiate, and spam. We want a more generic type for triage, so none of those
+              # fit here.
+              post.hide!(PostActionType.types[:notify_moderators]) if flag_type == :review_hide
             end
           end
         end
diff --git a/spec/lib/modules/automation/llm_triage_spec.rb b/spec/lib/modules/automation/llm_triage_spec.rb
index e9c9979a..bbff9e10 100644
--- a/spec/lib/modules/automation/llm_triage_spec.rb
+++ b/spec/lib/modules/automation/llm_triage_spec.rb
@@ -128,6 +128,26 @@ describe DiscourseAi::Automation::LlmTriage do
     expect(post.user.silenced?).to eq(true)
   end
 
+  it "can handle flag + hide" do
+    DiscourseAi::Completions::Llm.with_prepared_responses(["bad"]) do
+      triage(
+        post: post,
+        model: "custom:#{llm_model.id}",
+        system_prompt: "test %%POST%%",
+        search_for_text: "bad",
+        flag_post: true,
+        flag_type: :review_hide,
+        automation: nil,
+      )
+    end
+
+    reviewable = ReviewablePost.last
+
+    expect(reviewable.target).to eq(post)
+    expect(reviewable.reviewable_scores.first.reason).to include("bad")
+    expect(post.reload).to be_hidden
+  end
+
   it "does not silence the user if the flag fails" do
     Fabricate(
       :post_action,