diff --git a/enterprise/app/jobs/captain/llm/conversation_faq_job.rb b/enterprise/app/jobs/captain/llm/conversation_faq_job.rb
new file mode 100644
index 000000000..fa0fe45dd
--- /dev/null
+++ b/enterprise/app/jobs/captain/llm/conversation_faq_job.rb
@@ -0,0 +1,15 @@
+class Captain::Llm::ConversationFaqJob < ApplicationJob
+  queue_as :low
+
+  def perform(conversation)
+    inbox = conversation.inbox
+
+    return unless conversation.resolved?
+    return unless inbox.captain_active?
+
+    assistant = inbox.captain_assistant
+    return if assistant.config['feature_faq'].blank?
+
+    Captain::Llm::ConversationFaqService.new(assistant, conversation).generate_suggestions
+  end
+end
diff --git a/enterprise/app/listeners/captain_listener.rb b/enterprise/app/listeners/captain_listener.rb
index 879fb2b7e..611bf7a68 100644
--- a/enterprise/app/listeners/captain_listener.rb
+++ b/enterprise/app/listeners/captain_listener.rb
@@ -8,6 +8,6 @@ class CaptainListener < BaseListener
     return unless conversation.inbox.captain_active?
 
     Captain::Llm::ContactNotesService.new(assistant, conversation).generate_and_update_notes if assistant.config['feature_memory'].present?
-    Captain::Llm::ConversationFaqService.new(assistant, conversation).generate_and_deduplicate if assistant.config['feature_faq'].present?
+    Captain::Llm::ConversationFaqJob.perform_later(conversation) if assistant.config['feature_faq'].present?
   end
 end
diff --git a/enterprise/app/services/captain/llm/conversation_faq_prompts_service.rb b/enterprise/app/services/captain/llm/conversation_faq_prompts_service.rb
index dd0df4a6c..155e10a06 100644
--- a/enterprise/app/services/captain/llm/conversation_faq_prompts_service.rb
+++ b/enterprise/app/services/captain/llm/conversation_faq_prompts_service.rb
@@ -57,12 +57,12 @@ class Captain::Llm::ConversationFaqPromptsService
       PROMPT
     end
 
-    def equivalence_classifier
+    def same_faq
       <<~PROMPT
-        Decide whether the candidate and existing entries represent the same reusable FAQ.
+        Decide whether the new FAQ and existing FAQ are the same.
 
-        Return `same_faq` as true only when both questions have the same user intent and both answers give the same substantive guidance.
-        Wording, grammar, level of detail, and examples may differ. Return false when either entry adds, removes, contradicts, or changes a condition,
+        Return `same_faq` as true only when both questions ask the same thing and both answers give the same guidance.
+        Wording, grammar, level of detail, and examples may differ. Return false when either FAQ adds, removes, contradicts, or changes a condition,
         policy, procedure, audience, product, plan, time frame, or outcome. Related FAQs are not the same FAQ. When uncertain, return false.
 
         Return only valid JSON in this exact structure:
diff --git a/enterprise/app/services/captain/llm/conversation_faq_service.rb b/enterprise/app/services/captain/llm/conversation_faq_service.rb
index 44c9f1960..d0af18311 100644
--- a/enterprise/app/services/captain/llm/conversation_faq_service.rb
+++ b/enterprise/app/services/captain/llm/conversation_faq_service.rb
@@ -13,7 +13,7 @@ class Captain::Llm::ConversationFaqService < Llm::BaseAiService
     @embedding_service = Captain::Llm::EmbeddingService.new(account_id: conversation.account_id)
   end
 
-  def generate_and_deduplicate
+  def generate_suggestions
     return [] if no_human_interaction?
 
     generate.map { |faq| route_candidate(faq) }
@@ -31,6 +31,7 @@ class Captain::Llm::ConversationFaqService < Llm::BaseAiService
     embedding = embedding_service.get_embedding(candidate_text(faq))
 
     return discard_observation(faq) if matching_record(approved_faqs_for_language, faq, embedding)
+    return discard_observation(faq) if matching_record(dismissed_suggestions_for_language, faq, embedding)
 
     suggestion = matching_record(open_suggestions_for_language, faq, embedding)
     suggestion ||= assistant.faq_suggestions.create!(
@@ -66,8 +67,8 @@ class Captain::Llm::ConversationFaqService < Llm::BaseAiService
       candidate: candidate.slice('question', 'answer'),
       existing: { question: existing_record.question, answer: existing_record.answer }
     }
-    prompt = Captain::Llm::ConversationFaqPromptsService.equivalence_classifier
-    response = instrument_llm_call(equivalence_instrumentation_params(prompt, comparison)) do
+    prompt = Captain::Llm::ConversationFaqPromptsService.same_faq
+    response = instrument_llm_call(match_instrumentation_params(prompt, comparison)) do
       chat
         .with_params(response_format: { type: 'json_object' })
         .with_instructions(prompt)
@@ -79,7 +80,7 @@ class Captain::Llm::ConversationFaqService < Llm::BaseAiService
 
     JSON.parse(response_content).fetch('same_faq', false) == true
   rescue JSON::ParserError, RubyLLM::Error => e
-    Rails.logger.error "FAQ equivalence classification failed: #{e.message}"
+    Rails.logger.error "FAQ match failed: #{e.message}"
     false
   end
 
@@ -114,6 +115,10 @@ class Captain::Llm::ConversationFaqService < Llm::BaseAiService
     assistant.faq_suggestions.where(account_id: conversation.account_id).open.by_language(faq_language)
   end
 
+  def dismissed_suggestions_for_language
+    assistant.faq_suggestions.where(account_id: conversation.account_id).dismissed.by_language(faq_language)
+  end
+
   def approved_faqs_for_language
     return assistant.responses.approved if faq_language == account_language
 
@@ -153,14 +158,14 @@ class Captain::Llm::ConversationFaqService < Llm::BaseAiService
     }
   end
 
-  def equivalence_instrumentation_params(prompt, comparison)
+  def match_instrumentation_params(prompt, comparison)
     {
-      span_name: 'llm.captain.faq_equivalence',
+      span_name: 'llm.captain.faq_match',
       model: model,
       temperature: temperature,
       account_id: conversation.account_id,
       conversation_id: conversation.display_id,
-      feature_name: 'conversation_faq_deduplication',
+      feature_name: 'conversation_faq_match',
       messages: [
         { role: 'system', content: prompt },
         { role: 'user', content: comparison.to_json }
diff --git a/spec/enterprise/listeners/captain_listener_spec.rb b/spec/enterprise/listeners/captain_listener_spec.rb
index e076a8b8f..d1fcbe95e 100644
--- a/spec/enterprise/listeners/captain_listener_spec.rb
+++ b/spec/enterprise/listeners/captain_listener_spec.rb
@@ -29,7 +29,7 @@ describe CaptainListener do
           .to receive(:new)
           .with(assistant, conversation)
           .and_return(instance_double(Captain::Llm::ContactNotesService, generate_and_update_notes: nil))
-        expect(Captain::Llm::ConversationFaqService).not_to receive(:new)
+        expect(Captain::Llm::ConversationFaqJob).not_to receive(:perform_later)
 
         listener.conversation_resolved(event)
       end
@@ -42,11 +42,8 @@ describe CaptainListener do
         assistant.save!
       end
 
-      it 'generates and deduplicates FAQs' do
-        expect(Captain::Llm::ConversationFaqService)
-          .to receive(:new)
-          .with(assistant, conversation)
-          .and_return(instance_double(Captain::Llm::ConversationFaqService, generate_and_deduplicate: false))
+      it 'enqueues FAQ suggestion generation' do
+        expect(Captain::Llm::ConversationFaqJob).to receive(:perform_later).with(conversation)
         expect(Captain::Llm::ContactNotesService).not_to receive(:new)
 
         listener.conversation_resolved(event)
diff --git a/spec/enterprise/services/captain/llm/conversation_faq_service_spec.rb b/spec/enterprise/services/captain/llm/conversation_faq_service_spec.rb
index 9c2021190..5c92992cf 100644
--- a/spec/enterprise/services/captain/llm/conversation_faq_service_spec.rb
+++ b/spec/enterprise/services/captain/llm/conversation_faq_service_spec.rb
@@ -28,7 +28,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
     allow(mock_chat).to receive(:ask).and_return(mock_response)
   end
 
-  describe '#generate_and_deduplicate' do
+  describe '#generate_suggestions' do
     context 'when successful' do
       before do
         allow(embedding_service).to receive(:get_embedding).and_return(embedding_one, embedding_two)
@@ -39,7 +39,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
           model: Llm::Models.default_model_for('conversation_faq_generation')
         ).and_return(mock_chat)
 
-        described_class.new(captain_assistant, conversation).generate_and_deduplicate
+        described_class.new(captain_assistant, conversation).generate_suggestions
       end
 
       it 'uses the conversation FAQ default ahead of the legacy global installation model' do
@@ -49,7 +49,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
           model: Llm::Models.default_model_for('conversation_faq_generation')
         ).and_return(mock_chat)
 
-        described_class.new(captain_assistant, conversation).generate_and_deduplicate
+        described_class.new(captain_assistant, conversation).generate_suggestions
       end
 
       it 'keeps account conversation FAQ model overrides ahead of the feature default' do
@@ -58,7 +58,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
 
         expect(RubyLLM).to receive(:chat).with(model: 'gpt-4.1-mini').and_return(mock_chat)
 
-        described_class.new(captain_assistant, conversation).generate_and_deduplicate
+        described_class.new(captain_assistant, conversation).generate_suggestions
       end
 
       it 'resolves the feature model from the conversation account' do
@@ -67,7 +67,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
           account: conversation.account
         ).and_call_original
 
-        described_class.new(captain_assistant, conversation).generate_and_deduplicate
+        described_class.new(captain_assistant, conversation).generate_suggestions
       end
 
       it 'sends only customer and human support agent messages to the LLM' do
@@ -85,7 +85,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
         create(:message, conversation: conversation, account: conversation.account, inbox: conversation.inbox,
                          message_type: :activity, content: 'Activity message')
 
-        service.generate_and_deduplicate
+        service.generate_suggestions
 
         expected_content = satisfy do |content|
           content.include?('User: Customer question') &&
@@ -105,7 +105,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
                          sender: nil, message_type: :outgoing, content: 'Human replied from the native app',
                          content_attributes: { external_echo: true })
 
-        service.generate_and_deduplicate
+        service.generate_suggestions
 
         expected_content = satisfy do |content|
           content.include?('User: Customer asks in a native channel') &&
@@ -134,19 +134,19 @@ RSpec.describe Captain::Llm::ConversationFaqService do
           block.call
         end
 
-        service.generate_and_deduplicate
+        service.generate_suggestions
       end
 
       it 'creates suggestions instead of trusted FAQs for valid conversation content' do
         expect do
-          service.generate_and_deduplicate
+          service.generate_suggestions
         end.to change(captain_assistant.faq_suggestions, :count).by(2)
         expect(Captain::FaqObservation.count).to eq(2)
         expect(captain_assistant.responses.count).to be_zero
       end
 
       it 'saves open suggestions with one attached source each' do
-        service.generate_and_deduplicate
+        service.generate_suggestions
         expect(
           captain_assistant.faq_suggestions.pluck(:question, :answer, :status, :source_count, :language)
         ).to contain_exactly(
@@ -163,12 +163,12 @@ RSpec.describe Captain::Llm::ConversationFaqService do
       let(:conversation) { create(:conversation) }
 
       it 'returns an empty array without generating FAQs' do
-        expect(service.generate_and_deduplicate).to eq([])
+        expect(service.generate_suggestions).to eq([])
       end
 
       it 'does not call the LLM API' do
         expect(RubyLLM).not_to receive(:chat)
-        service.generate_and_deduplicate
+        service.generate_suggestions
       end
     end
 
@@ -177,19 +177,19 @@ RSpec.describe Captain::Llm::ConversationFaqService do
         create(:captain_assistant_response, assistant: captain_assistant, account: captain_assistant.account,
                                             question: 'Similar question', answer: 'Similar answer', embedding: embedding_one)
       end
-      let(:equivalence_response) { instance_double(RubyLLM::Message, content: { same_faq: true }.to_json) }
+      let(:match_response) { instance_double(RubyLLM::Message, content: { same_faq: true }.to_json) }
 
       before do
         existing_response
         allow(embedding_service).to receive(:get_embedding).and_return(embedding_one)
         allow(mock_chat).to receive(:ask) do |input|
-          input.start_with?('{') ? equivalence_response : mock_response
+          input.start_with?('{') ? match_response : mock_response
         end
       end
 
       it 'discards candidates the LLM confirms are covered by an approved FAQ' do
         expect do
-          service.generate_and_deduplicate
+          service.generate_suggestions
         end.to change(Captain::FaqObservation.discarded, :count).by(2)
         expect(captain_assistant.faq_suggestions.count).to be_zero
       end
@@ -212,19 +212,19 @@ RSpec.describe Captain::Llm::ConversationFaqService do
           suggestion.update!(source_count: suggestion.observations.attached.count)
         end
       end
-      let(:equivalence_response) { instance_double(RubyLLM::Message, content: { same_faq: true }.to_json) }
+      let(:match_response) { instance_double(RubyLLM::Message, content: { same_faq: true }.to_json) }
 
       before do
         existing_suggestion
         allow(embedding_service).to receive(:get_embedding).and_return(embedding_one)
         allow(mock_chat).to receive(:ask) do |input|
-          input.start_with?('{') ? equivalence_response : mock_response
+          input.start_with?('{') ? match_response : mock_response
         end
       end
 
       it 'attaches the observation and increments the source count' do
         expect do
-          service.generate_and_deduplicate
+          service.generate_suggestions
         end.to change(existing_suggestion.observations, :count).by(1)
         expect(existing_suggestion.reload.source_count).to eq(2)
         expect(captain_assistant.faq_suggestions.count).to eq(1)
@@ -245,7 +245,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
 
       it 'creates a separate suggestion in the conversation language' do
         expect do
-          service.generate_and_deduplicate
+          service.generate_suggestions
         end.to change(captain_assistant.faq_suggestions, :count).by(1)
 
         expect(captain_assistant.faq_suggestions.pluck(:language)).to contain_exactly('en', 'pt')
@@ -267,19 +267,19 @@ RSpec.describe Captain::Llm::ConversationFaqService do
           source_count: 1
         )
       end
-      let(:equivalence_response) { instance_double(RubyLLM::Message, content: { same_faq: true }.to_json) }
+      let(:match_response) { instance_double(RubyLLM::Message, content: { same_faq: true }.to_json) }
 
       before do
         existing_suggestion
         allow(embedding_service).to receive(:get_embedding).and_return(embedding_one)
         allow(mock_chat).to receive(:ask) do |input|
-          input.start_with?('{') ? equivalence_response : mock_response
+          input.start_with?('{') ? match_response : mock_response
         end
       end
 
       it 'attaches the observation to the existing base-language suggestion' do
         expect do
-          service.generate_and_deduplicate
+          service.generate_suggestions
         end.to change(existing_suggestion.observations, :count).by(1)
 
         expect(existing_suggestion.reload.source_count).to eq(2)
@@ -301,7 +301,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
 
       it 'does not discard a candidate in another language' do
         expect do
-          service.generate_and_deduplicate
+          service.generate_suggestions
         end.to change(captain_assistant.faq_suggestions, :count).by(1)
         expect(Captain::FaqObservation.discarded.count).to be_zero
         expect(captain_assistant.faq_suggestions.last.language).to eq('pt')
@@ -320,19 +320,19 @@ RSpec.describe Captain::Llm::ConversationFaqService do
                                             question: 'Como ativo o recurso?', answer: 'Ative nas configuracoes.',
                                             embedding: embedding_one)
       end
-      let(:equivalence_response) { instance_double(RubyLLM::Message, content: { same_faq: true }.to_json) }
+      let(:match_response) { instance_double(RubyLLM::Message, content: { same_faq: true }.to_json) }
 
       before do
         existing_response
         allow(embedding_service).to receive(:get_embedding).and_return(embedding_one)
         allow(mock_chat).to receive(:ask) do |input|
-          input.start_with?('{') ? equivalence_response : mock_response
+          input.start_with?('{') ? match_response : mock_response
         end
       end
 
       it 'deduplicates against approved FAQs in the same base language' do
         expect do
-          service.generate_and_deduplicate
+          service.generate_suggestions
         end.to change(Captain::FaqObservation.discarded, :count).by(2)
         expect(captain_assistant.faq_suggestions.count).to be_zero
       end
@@ -346,7 +346,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
 
       it 'returns empty array and logs the error' do
         expect(Rails.logger).to receive(:error).with('LLM API Error: API Error')
-        expect(service.generate_and_deduplicate).to eq([])
+        expect(service.generate_suggestions).to eq([])
       end
     end
 
@@ -361,7 +361,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
 
       it 'handles JSON parsing errors gracefully' do
         expect(Rails.logger).to receive(:error).with(/Error in parsing GPT processed response:/)
-        expect(service.generate_and_deduplicate).to eq([])
+        expect(service.generate_suggestions).to eq([])
       end
     end
 
@@ -375,7 +375,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
       end
 
       it 'returns empty array' do
-        expect(service.generate_and_deduplicate).to eq([])
+        expect(service.generate_suggestions).to eq([])
       end
     end
   end
@@ -398,7 +398,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
           .at_least(:once)
           .and_call_original
 
-        service.generate_and_deduplicate
+        service.generate_suggestions
       end
     end
 
@@ -420,7 +420,7 @@ RSpec.describe Captain::Llm::ConversationFaqService do
           .at_least(:once)
           .and_call_original
 
-        service.generate_and_deduplicate
+        service.generate_suggestions
       end
     end
   end