Merge remote-tracking branch 'upstream/main' into add-GUI

README.md

@@ -2,24 +2,26 @@
 
 # OpenAdapt: AI-First Process Automation with Transformers
 
+<img width="853" alt="image" src="https://github.com/MLDSAI/OpenAdapt/assets/774615/438e7803-667c-4ce8-a135-1d1e10700ced">
+
 Welcome to OpenAdapt! This Python library implements AI-First Process Automation
 with the power of Transformers by:
 
 - Recording screenshots and associated user input
 - Aggregating and visualizing user input and recordings for development
-- Converting screenshots and user input into tok/enized format
+- Converting screenshots and user input into tokenized format
 - Generating synthetic input via transformer model completions
 - Replaying synthetic input to complete tasks
 
 The goal is similar to that of
 [Robotic Process Automation](https://en.wikipedia.org/wiki/Robotic_process_automation),
 except that we use transformers instead of conventional RPA tools.
 
-The approach is similar to [adept.ai](https://adept.ai/), with some key differences:
-1. Instead of requiring the user to prompt the model directly, we prompt it behind the
-scenes by observing the user's activities;
-2. We work with all types of desktop applications, not just web apps;
-3. We're open source!
+The direction is adjacent to [Adept.ai](https://adept.ai/), with some key differences:
+1. OpenAdapt is model agnostic;
+1. OpenAdapt generates prompts automatically (auto-prompted, not user-prompted);
+2. OpenAdapt works with all types of desktop GUIs, including virtualized (e.g. Citrix) and web
+3. OpenAdapt is open source! (license TBD, please see https://github.com/MLDSAI/OpenAdapt/issues/246)
 
 ## Install
 
@@ -95,8 +97,6 @@ More ReplayStrategies coming soon! (see [Contributing](#Contributing)).
 
 ## Contributing
 
-### Design
-
 ### Problem Statement
 
 Our goal is to automate the task described and demonstrated in a `Recording`.