Blanket UX Changes - WIP

playbooks/core/comfyui-image-gen/README.md

@@ -22,7 +22,17 @@ This tutorial teaches you how to use ComfyUI with the Z Image Turbo model on you
 - Generating images and tuning generation parameters
 - Saving and sharing workflows
 
-## Installing Dependencies
+## Setting the Memory Configuration
+
+<!-- @setup:memory-config -->
+
+<!-- @device:halo_box -->
+## Check for Software Updates
+
+<!-- @setup:software-update -->
+<!-- @device:end -->
+
+## Installing Software Prerequisites
 
 <!-- @os:windows -->
 <!-- @require:driver,comfyui -->
@@ -31,18 +41,24 @@ This tutorial teaches you how to use ComfyUI with the Z Image Turbo model on you
 <!-- @os:linux -->
 
 <!-- @device:halo,stx,krk,rx7900xt,rx9070xt -->
+**Grant your user access to GPU devices** (log out and back in for this to take effect):
+
+```bash
+sudo usermod -aG render,video $LOGNAME
+```
+
 #### Create a Virtual Environment
 On Linux, open a terminal in the directory of your choice and run the following prompt to create a venv:
 
 ```bash
 sudo apt update
 sudo apt install -y python3-venv
-python3 -m venv llm-env
-source llm-env/bin/activate
+python3 -m venv comfyui-env
+source comfyui-env/bin/activate
 ```
 <!-- @device:end -->
 
-<!-- @require:driver,rocm,pytorch,comfyui -->
+<!-- @require:driver,pytorch,comfyui -->
 <!-- @os:end -->
 
 <!-- @os:windows -->
@@ -271,8 +287,6 @@ echo "OK: ComfyUI server is reachable!"
 <!-- @test:end --> 
 <!-- @os:end -->
 
-
-
 ## Launching ComfyUI
 
 <!-- @device:halo_box -->

playbooks/core/comfyui-image-gen/playbook.json

@@ -1,6 +1,6 @@
 {
   "id": "comfyui-image-gen",
-  "title": "Generating images with ComfyUI and Z Image Turbo",
+  "title": "Generate Images with ComfyUI",
   "description": "Create stunning AI-generated images using ComfyUI with Z Image Turbo.",
   "time": 15,
   "unsupported_platforms": {

playbooks/core/lmstudio-rocm-llms/README.md

@@ -20,9 +20,20 @@ LM Studio is a powerful GUI-based wrapper for [llama.cpp](https://github.com/ggm
 - Serve models via OpenAI Compatible API to power custom workflows and apps
 
 
-## Installing Dependencies
+## Setting the Memory Configuration
 
-<!-- @require:lmstudio,memory-config -->
+<!-- @setup:memory-config -->
+
+<!-- @device:halo_box -->
+## Check for Software Updates
+> **Note**: If VSCode is not installed, you can install it with Ryzen AI Developer Center.
+
+<!-- @setup:software-update -->
+<!-- @device:end -->
+
+## Installing Software Prerequisites
+
+<!-- @require:lmstudio -->
 
 ## Downloading Models
 
@@ -120,54 +131,60 @@ This model will now be accessible through the LM Studio Server endpoint and will
 Having just created the OpenAI Compatible endpoint, let's look at how to integrate this into a Python developer environment (such as VSCode) and use your system as a local API Provider. 
 
 1. Create a Python virtual environment:
+
+<!-- @os:linux -->
 <!-- @device:halo_box -->
-<!-- @os:windows -->
-    On Windows, open a terminal in the directory of your choice and follow the commands to create a venv.
+    On Linux, open a terminal in the directory of your choice and follow the commands to create a venv.
     ```bash
-    python -m venv llm-env --system-site-packages
-    llm-env\Scripts\activate
+    sudo apt update
+    sudo apt install -y python3-venv
+    python3 -m venv lmstudio-env --system-site-packages
+    source lmstudio-env/bin/activate
     ```
+<!-- @device:end -->
 
-    > **Tip**: Windows users may need to modify their PowerShell Execution Policy (e.g.
-    > setting it to RemoteSigned or Unrestricted) before running some Powershell commands.
+<!-- @device:halo,stx,krk,rx7900xt,rx9070xt -->
+**Grant your user access to GPU devices** (log out and back in for this to take effect):
 
-<!-- @os:end -->
+```bash
+sudo usermod -aG render,video $LOGNAME
+```
 
-<!-- @os:linux -->
     On Linux, open a terminal in the directory of your choice and follow the commands to create a venv.
     ```bash
     sudo apt update
     sudo apt install -y python3-venv
-    python3 -m venv llm-env --system-site-packages
-    source llm-env/bin/activate
+    python3 -m venv lmstudio-env
+    source lmstudio-env/bin/activate
     ```
-<!-- @os:end -->
 <!-- @device:end -->
+<!-- @os:end -->
 
-
-<!-- @device:halo,stx,krk,rx7900xt,rx9070xt -->
 <!-- @os:windows -->
+<!-- @device:halo_box -->
     On Windows, open a terminal in the directory of your choice and follow the commands to create a venv.
     ```bash
-    python -m venv llm-env
-    llm-env\Scripts\activate
+    python -m venv lmstudio-env --system-site-packages
+    lmstudio-env\Scripts\activate
     ```
 
     > **Tip**: Windows users may need to modify their PowerShell Execution Policy (e.g.
     > setting it to RemoteSigned or Unrestricted) before running some Powershell commands.
 
-<!-- @os:end -->
+<!-- @device:end -->
 
-<!-- @os:linux -->
-    On Linux, open a terminal in the directory of your choice and follow the commands to create a venv.
+<!-- @device:halo,stx,krk,rx7900xt,rx9070xt -->
+    On Windows, open a terminal in the directory of your choice and follow the commands to create a venv.
     ```bash
-    sudo apt update
-    sudo apt install -y python3-venv
-    python3 -m venv llm-env
-    source llm-env/bin/activate
+    python -m venv lmstudio-env
+    lmstudio-env\Scripts\activate
     ```
-<!-- @os:end -->
+
+    > **Tip**: Windows users may need to modify their PowerShell Execution Policy (e.g.
+    > setting it to RemoteSigned or Unrestricted) before running some Powershell commands.
+
 <!-- @device:end -->
+<!-- @os:end -->
 
 2. Install the OpenAI package
     ```bash

playbooks/core/lmstudio-rocm-llms/playbook.json

@@ -1,6 +1,6 @@
 {
   "id": "lmstudio-rocm-llms",
-  "title": "Running and serving LLMs with LM Studio",
+  "title": "Run and Serve LLMs with LM Studio",
   "description": "Set up LM Studio and LM Studio Server to run and serve large language models locally.",
   "time": 30,
   "supported_platforms": {

playbooks/core/n8n-automation-gpt-oss/README.md

@@ -35,7 +35,17 @@ In this playbook, we use Lemonade to serve a local LLM that n8n connects to for
 
 n8n includes a **native Lemonade node** (`Lemonade Chat Model`) that provides a first-class integration - no need for manual configuration. This makes connecting your local LLM to automation workflows straightforward.
 
-## Prerequisites
+## Setting the Memory Configuration
+
+<!-- @setup:memory-config -->
+
+<!-- @device:halo_box -->
+## Check for Software Updates
+
+<!-- @setup:software-update -->
+<!-- @device:end -->
+
+## Installing Software Prerequisites
 <!-- @os:windows -->
 <!-- @require:lemonade,nodejs -->
 <!-- @os:end -->

playbooks/core/n8n-automation-gpt-oss/assets/compose.yml

@@ -1,6 +1,6 @@
 services:
   n8n:
-    image: docker.n8n.io/n8nio/n8n
+    image: docker.io/n8nio/n8n
     container_name: n8n
     restart: unless-stopped
     network_mode: host

playbooks/core/n8n-automation-gpt-oss/playbook.json

@@ -2,7 +2,7 @@
   "id": "n8n-automation-gpt-oss",
   "title": "Automating Workflows with n8n and Local LLMs",
   "description": "Build an AI-powered news summarizer using n8n and Lemonade.",
-  "time": 30,
+  "time": 45,
   "supported_platforms": {
     "halo": [
       "linux",
@@ -59,7 +59,7 @@
       "windows"
     ]
   },
-  "difficulty": "beginner",
+  "difficulty": "intermediate",
   "isNew": false,
   "isFeatured": false,
   "developed": true,

playbooks/core/pytorch-rocm-llms/README.md

@@ -24,74 +24,90 @@ This tutorial uses PyTorch powered by AMD ROCm™ software to run models that ca
 - Run LLMs like gpt-oss-20b and qwen3.5-4B locally using PyTorch and ROCm
 - Create a document summarization tool using LLMs
 
-## Initial Setup 
+## Setting the Memory Configuration
+
+<!-- @setup:memory-config -->
+
+<!-- @device:halo_box -->
+## Check for Software Updates
+> **Note**: If VSCode is not installed, you can install it with Ryzen AI Developer Center.
+
+<!-- @setup:software-update -->
+<!-- @device:end -->
+
+## Installing Software Prerequisites
 
 ### Create a Virtual Environment
 
+<!-- @os:linux -->
 <!-- @device:halo_box -->
-<!-- @os:windows -->
-On Windows, open a terminal in the directory of your choice and follow the commands to create a venv with ROCm+Pytorch already installed.
-<!-- @test:id=create-venv timeout=60 -->
+On Linux, open a terminal in the directory of your choice and follow the commands to create a venv with ROCm+Pytorch already installed.
+<!-- @test:id=create-venv timeout=120 -->
 ```bash
-python -m venv llm-env --system-site-packages
-llm-env\Scripts\activate
+sudo apt update
+sudo apt install -y python3-venv
+python3 -m venv pytorch-env --system-site-packages
+source pytorch-env/bin/activate
 ```
 <!-- @test:end -->
+<!-- @setup:id=activate-venv command="source pytorch-env/bin/activate" -->
+<!-- @device:end -->
 
-> **Tip**: Windows users may need to modify their PowerShell Execution Policy (e.g.
-> setting it to RemoteSigned or Unrestricted) before running some Powershell commands.
+<!-- @device:halo,stx,krk,rx7900xt,rx9070xt -->
+**Grant your user access to GPU devices** (log out and back in for this to take effect):
 
-<!-- @setup:id=activate-venv command="llm-env\Scripts\activate.bat" -->
-<!-- @os:end -->
+```bash
+sudo usermod -aG render,video $LOGNAME
+```
 
-<!-- @os:linux -->
-On Linux, open a terminal in the directory of your choice and follow the commands to create a venv with ROCm+Pytorch already installed.
+On Linux, open a terminal in the directory of your choice and follow the commands to create a venv.
 <!-- @test:id=create-venv timeout=120 -->
 ```bash
 sudo apt update
 sudo apt install -y python3-venv
-python3 -m venv llm-env --system-site-packages
-source llm-env/bin/activate
+python3 -m venv pytorch-env
+source pytorch-env/bin/activate
 ```
 <!-- @test:end -->
-<!-- @setup:id=activate-venv command="source llm-env/bin/activate" -->
-<!-- @os:end -->
+<!-- @setup:id=activate-venv command="source pytorch-env/bin/activate" -->
 <!-- @device:end -->
+<!-- @os:end -->
 
-
-<!-- @device:halo,stx,krk,rx7900xt,rx9070xt -->
 <!-- @os:windows -->
-On Windows, open a terminal in the directory of your choice and follow the commands to create a venv.
+<!-- @device:halo_box -->
+On Windows, open a terminal in the directory of your choice and follow the commands to create a venv with ROCm+Pytorch already installed.
 <!-- @test:id=create-venv timeout=60 -->
 ```bash
-python -m venv llm-env
-llm-env\Scripts\activate
+python -m venv pytorch-env --system-site-packages
+pytorch-env\Scripts\activate
 ```
 <!-- @test:end -->
 
 > **Tip**: Windows users may need to modify their PowerShell Execution Policy (e.g.
 > setting it to RemoteSigned or Unrestricted) before running some Powershell commands.
 
-<!-- @setup:id=activate-venv command="llm-env\Scripts\activate.bat" -->
-<!-- @os:end -->
+<!-- @setup:id=activate-venv command="pytorch-env\Scripts\activate.bat" -->
+<!-- @device:end -->
 
-<!-- @os:linux -->
-On Linux, open a terminal in the directory of your choice and follow the commands to create a venv.
-<!-- @test:id=create-venv timeout=120 -->
+<!-- @device:halo,stx,krk,rx7900xt,rx9070xt -->
+On Windows, open a terminal in the directory of your choice and follow the commands to create a venv.
+<!-- @test:id=create-venv timeout=60 -->
 ```bash
-sudo apt update
-sudo apt install -y python3-venv
-python3 -m venv llm-env
-source llm-env/bin/activate
+python -m venv pytorch-env
+pytorch-env\Scripts\activate
 ```
 <!-- @test:end -->
-<!-- @setup:id=activate-venv command="source llm-env/bin/activate" -->
-<!-- @os:end -->
+
+> **Tip**: Windows users may need to modify their PowerShell Execution Policy (e.g.
+> setting it to RemoteSigned or Unrestricted) before running some Powershell commands.
+
+<!-- @setup:id=activate-venv command="pytorch-env\Scripts\activate.bat" -->
 <!-- @device:end -->
+<!-- @os:end -->
 
 ### Installing Basic Dependencies
 <!-- @os:linux -->
-<!-- @require:driver,rocm,pytorch -->
+<!-- @require:driver,pytorch -->
 <!-- @os:end -->
 <!-- @os:windows -->
 <!-- @require:driver,pytorch -->

playbooks/core/pytorch-rocm-llms/playbook.json

@@ -1,6 +1,6 @@
 {
   "id": "pytorch-rocm-llms",
-  "title": "Running LLMs with PyTorch and AMD ROCm™ software",
+  "title": "Run LLMs with PyTorch and ROCm™",
   "description": "Learn to run powerful language models on your PC with PyTorch and AMD ROCm™ software to summarize documents quickly and easily.",
   "time": 30,
   "supported_platforms": {

playbooks/core/vscode-qwen3-coder/README.md

@@ -9,8 +9,6 @@ SPDX-License-Identifier: MIT
 > This playbook uses special tags that GitHub cannot render. Please visit [amd.com/playbooks](https://amd.com/playbooks) to correctly preview this content.
 <!-- @github-only:end -->
 
-# Local LLM coding with VSCode and Qwen3-Coder-30B
-
 <!-- @device:stx,krk -->
 > [!NOTE]
 > This playbook requires a minimum of **32GB** of system memory.
@@ -28,7 +26,18 @@ This tutorial demonstrates how to use Cline, VS Code, and LM Studio to run a cod
 * How to configure Cline to communicate with LM Studio for local inference of coding agents.
 * How to use local coding agents to solve real-world software engineering tasks. 
 
-## Core Dependencies
+## Setting the Memory Configuration
+
+<!-- @setup:memory-config -->
+
+<!-- @device:halo_box -->
+## Check for Software Updates
+
+> **Note**: If VSCode is not installed, you can install it with Ryzen AI Developer Center.
+<!-- @setup:software-update -->
+<!-- @device:end -->
+
+## Installing Software Prerequisites
 
 <!-- @require:lmstudio,vscode -->