Update README.md

Author: mlejva

README.md

@@ -12,6 +12,10 @@ Follow E2B on [X (Twitter)](https://twitter.com/e2b_dev)
 
 <img width="1200" alt="Post-02" src="https://github.com/e2b-dev/code-interpreter/assets/5136688/2fa8c371-f03c-4186-b0b6-4151e68b0539">
 
+## Custom E2B sandbox with Code Interpreter SDK
+
+Follow [this guide](./template/README.md) if you want to customize the Code Interprerter sandbox (e.g.: add a preinstalled package). The customization is done via [custom E2B sandbox template](https://e2b.dev/docs/sandbox/templates/overview).
+
 ## Installation
 
 ### Python
@@ -180,11 +184,6 @@ await sandbox.notebook.execCell(code, {
 await sandbox.close()
 ```
 
-## Custom E2B sandbox with Code Interpreter SDK
-
-The template requires custom setup. If you want to build your own custom template and use Code Interpreter, look at [README.md](./template/README.md) in the template folder.
-
-
 ## How the SDK works
 The code generated by LLMs is often split into code blocks, where each subsequent block references the previous one. This is a common pattern in Jupyter notebooks, where each cell can reference the variables and definitions from the previous cells. In the classical sandbox each code execution is independent and does not share the context with the previous executions.