agent design pattern

app.py

@@ -149,7 +149,7 @@ With the right competitive research, you don’t just react to the market—you
       ],
       [in_verbatim]
     )
-    btn_recommend = gr.Button("Research", interactive=False)
+    btn_recommend = gr.Button("Research (Diabled used up all the token for LLM quota)", interactive=False)
     btn_recommend.click(fn=bestPractice, inputs=in_verbatim, outputs=out_product)
 
     gr.Markdown("""
@@ -220,6 +220,9 @@ How can we turn application security from a bottleneck into a competitive advant
 Product & revenue teams need confidence that customer-facing banking apps will not just ship fast—but also protect users and unlock new monetization opportunities.
 
 ### 💡 Proposed Solution
+Agent Design Pattern: https://x.com/i/status/1940342200216482211
+General System Design: https://pbs.twimg.com/media/FuKyiRIaAAEbC5B?format=jpg&name=900x900
+
 A multi-agent GenAI system trained on RBC’s codebase, policy docs, and threat data—
 that provides real-time, localized security feedback, explains why something’s a risk, and suggests secure-by-default alternatives.