diff --git a/docs/learn/llm_app_architectures.mdx b/docs/learn/llm_app_architectures.mdx
new file mode 100644
index 0000000000..6e4e48169a
--- /dev/null
+++ b/docs/learn/llm_app_architectures.mdx
@@ -0,0 +1,26 @@
+---
+title: 'LLM App Architectures'
+description: 'The different types of LLM applications.'
+---
+
+
+There are multitude of architectures or pipelines for LLM applications. We discuss here the main ones. 
+
+## The Single Prompt Architecture
+
+This architecture is the simplest. The LLM application is a simple wrapper around one prompt / LLM call. 
+
+In agenta you can [create such LLM apps from the UI](/quickstart/getting-started-ui). You can use your own code in case that your model is not supported (or you would like to add some custom logic for pre-processing or post-processing the inputs).
+
+<img className="dark:hidden" height="600" src="/images/learning/single_prompt_light.png" />
+<img className="hidden dark:block" height="600" src="/images/learning/single_prompt_dark.png" />
+
+
+## The Chain-of-prompt Architecture
+
+
+## The Retrieval Augment Generation Architecture
+
+## The Agent architecture
+
+## Chat vs. Flow
\ No newline at end of file