The latest AskUI update is available, and it’s packed with features that make automation smarter, easier, and more powerful than ever. Whether you’re streamlining web tasks, diving into AI-driven UI interactions, or customizing workflows to fit your needs, this release has something for everyone. Let’s explore how these exciting changes can transform the way you automate. Let’s jump into the good stuff!
One of the standout additions is the WebVisionAgent, powered by Playwright, which enables you to automate tasks directly within web browsers. From filling out forms to navigating complex web apps, it’s a game-changer for browser automation. Getting started is as simple as running pip install askui[web] to install the necessary dependencies. Alongside this, the act agent now includes two AI Element Tools: AskUIGetAskUIElementTool, which pinpoints UI elements by their semantic names and provides coordinates for precise interactions, and AskUIListAIElementTool, which gives you a list of all available AI elements to work with. These tools make navigating and manipulating UI elements feel effortless.
For those who love customization, AskUI now supports Bring Your Model (BYOM), allowing you to integrate custom models for unparalleled flexibility in your automation tasks. The platform has also been supercharged with Claude 4 integration, bringing more powerful AI capabilities to everything from the AndroidVisionAgent to your everyday automation needs. Plus, with OpenRouter, you can route act() commands to various models and track their performance, giving you greater control and insight into task execution.
AskUI’s agents have also received a major upgrade. The act() method now accepts tools and settings parameters for fine-tuned control, and new actions, such as scroll and wait, make complex interactions a breeze. You can now automate intricate keyboard shortcuts with press-and-hold and key release functionality, while the new Print Tool lets you log progress, updates, or errors to the console. Image-based goals have also been improved, letting you use screenshots or base64 images to guide automation with precision. And with extended get() functionality, querying and interacting with UI elements is more robust than ever.
Streamlined and Enhanced Architecture
Behind the scenes, AskUI has been refined for better performance and usability. The new AgentBase class makes agents more modular and extensible, while settings for the AskUI Inference API and Anthropic API are now more consistent and easier to use. The Chat API has been upgraded with a default port (9261) and is now hosted on the AskUI Hub at our AskUI page. Improved keyboard tooling supports a wider range of keys and modifier combinations, and the UI Control Client and Execution Runtime have been enhanced for reliable cross-platform connections. New tools like MouseDragAndDropTool, WaitTool, and PrintTool, along with updated AIElement Collection methods, give you even more ways to tackle advanced automation scenarios.
Important Changes to Know
To keep AskUI lightweight and modular, some breaking changes have been introduced. Core dependencies are now optional, so you’ll need to install extras based on your needs:
Perhaps the most exciting addition is an experimental feature that lets you create and interact with agents using natural language prompts through chat. Imagine automating tasks by simply describing them in plain English, and no complex scripts are needed. To try it, sign up at our AskUI page, follow the onboarding steps, run pip install askui, and start chatting with your agent. This feature is a glimpse into the future of automation, and we’re eager to hear your feedback as we refine it.
Building top-notch software doesn’t have to be a struggle. At NUCIDA, we’ve cracked the code with our B/R/AI/N Testwork testing solution - pairing our QA expertise with your test management tool to deliver streamlined processes, slick automation, and results you can count on. On time. Hassle-free. Ready to ditch future headaches? Let NUCIDA show you how!
Among others, NUCIDA's QA experts are certified consultants for Testiny, SmartBear, TestRail, and Xray software testing tools.
Why Choose NUCIDA?
For us, digitization does not just mean modernizing what already exists but, most importantly, reshaping the future. That is why we have made it our goal to provide our customers with sustainable support in digitizing the entire value chain. Our work has only one goal: your success!
Don’t let testing slow you down. Explore how consulting services can make your software quality soar - headache-free! Got questions? We’ve got answers. Let’s build something amazing together!
With these updates, AskUI is more powerful, flexible, and user-friendly than ever. Whether you’re automating web or Android tasks, integrating custom models, or exploring chat-based automation, AskUI has the tools to make it happen. Of course, the latest AskUI update offers much more. I have only highlighted a few of them in this blog. Head to our AskUI page to get started and see how these new features can elevate your automation workflows and software testing.
Have questions or want to know more about the latest developments in AskUI and AI-driven automation? The NUCIDA QA Team is here to help! Until then, let’s keep pushing the boundaries of testing together. Stay tuned, and happy testing!.
Want to know more? Watch our YouTube video, AskUI Vision Agent Demo 2025, to learn more about the usage and benefits of AskUI.
Logo and pictures from pixabay.com, AskUI, and NUCIDA Group
Article written and published by Torsten Zimmermann