links

Author: irvinebroque

src/content/docs/agents/patterns.mdx

@@ -18,7 +18,7 @@ Decomposes tasks into a sequence of steps, where each LLM call processes the out
 
 ![Figure 1: Prompt Chaining](~/assets/images/agents/01-prompt-chaining.jpg)
 
-[**Interactive Demo**](https://patterns.agents.workers.dev)
+[**Interactive Demo**](https://ai.cloudflare.com/anthropic-agent-patterns)
 
 <GitHubCode
 	repo="cloudflare/agents"
@@ -33,7 +33,7 @@ Classifies input and directs it to specialized followup tasks, allowing for sepa
 
 ![Figure 2: Routing](~/assets/images/agents/2_Routing.jpg)
 
-[**Interactive Demo**](https://patterns.agents.workers.dev)
+[**Interactive Demo**](https://ai.cloudflare.com/anthropic-agent-patterns)
 
 <GitHubCode
 	repo="cloudflare/agents"
@@ -48,7 +48,7 @@ Enables simultaneous task processing through sectioning or voting mechanisms.
 
 ![Figure 3: Parallelization](~/assets/images/agents/3_Parallelization.jpg)
 
-[**Interactive Demo**](https://patterns.agents.workers.dev)
+[**Interactive Demo**](https://ai.cloudflare.com/anthropic-agent-patterns)
 
 <GitHubCode
 	repo="cloudflare/agents"
@@ -63,7 +63,7 @@ A central LLM dynamically breaks down tasks, delegates to worker LLMs, and synth
 
 ![Figure 4: Orchestrator Workers](~/assets/images/agents/4_Orchestrator-Workers.jpg)
 
-[**Interactive Demo**](https://patterns.agents.workers.dev)
+[**Interactive Demo**](https://ai.cloudflare.com/anthropic-agent-patterns)
 
 <GitHubCode
 	repo="cloudflare/agents"
@@ -78,7 +78,7 @@ One LLM generates responses while another provides evaluation and feedback in a
 
 ![Figure 5: Evaluator-Optimizer](~/assets/images/agents/5_Evaluator-Optimizer.jpg)
 
-[**Interactive Demo**](https://patterns.agents.workers.dev)
+[**Interactive Demo**](https://ai.cloudflare.com/anthropic-agent-patterns)
 
 <GitHubCode
 	repo="cloudflare/agents"