Podcast

What do CTOs need to know about gen AI and testing? Have you tried or seen the new browser use tool yet and want to know a new tool to help you analyze and debug tests? Find out in this episode of the Test Guild News show for the week of March 16th. So grab your favorite cup of coffee or tea and let's do this. Hey, before we get into the news, I want to thank this week's sponsor, Zap Test AI, an AI driven platform that can help you supercharge your automation efforts. It's really cool because their Intelligent Copilot generates optimized code snippets while their Plan Studio can help you effortlessly streamline your test case management. And what's even better is you can experience the power of AI in action with their risk free 6 month proof of concept featuring a dedicated Zap expert at no upfront costs. Unlock unparalleled efficiency and ROI in your testing process. Don't wait. Schedule a demo now and see how it can help you improve your test automation efforts using the link down below all right, so first off, I'm blaming Jason Huggins for stunning me down this rabbit hole. We just posted this really quick thing on Browser automation really is having its day in the sun and I looked on the link he shared and it's all about browser use. So this little known AI tool, browser use is experiencing a surge in popularity. One of the main reasons because it's been actually integrated recently into the AI agent platform Manus. So if you don't know, Browse facilitates easier interaction between AI agents and websites. So browse interacts websites elements like buttons and widget, allowing AI models to interact with them. The tool also manages multiple browser tabs and handles various input methods. And its daily downloads have increased more than five fold in a week, reaching 28,000 on March 10 from approximately 5,000 on March 3. It's also freely available for self hosted versions and it's one of the things that's driving the increase in usage. Also, I didn't know about Manus, so I checked out Manus as well. Manus is also free and as I mentioned it's an AI agent platform and I asked it hey, how can you help with automation testing and software testing? And it listed 20 use cases that it can help with software testing as well. This is also free so it says it can help with test script generation, test case development, API test automation, UI testing, performance testing, load testing, security testing. It has a whole bunch of things it says it can help you with, especially when evaluating or implementing scans on your site or anything like that. I've been messing around with it. It is really, really cool, really powerful. So if you haven't tried browser use, you could definitely check it out within Manus. And it's all free as of now, so definitely check it out using the link down below. All right, next up is our Webinar of the Week. So traditional software testing methods are really struggling to keep pace with accelerated development cycles, leading to increased costs and delayed releases. So in this upcoming test guild, free training called Seamless, Scalable and Swift what Every CTO Should Know about Jenny I blink I.O. will be joining us to share the challenges of the current testing practices and showcase Gen's potential to address these issues. So this webinar is going to feature three awesome experts. The first one is Tal, who is the CEO of Blinkio. She's a veteran in the testing industry. We also have Sabnesh, who's the head of qa, who knows a bunch about real world applications of Gen AI and testing. And we also have Rebecca joining us who's also the Operations manager. And this webinar is going to include a live demonstration of Gen AI powered testing tools aim to provide attendees with practical insights into implementations and best practices of using it. And the key focus of this particular webinar is going to be on quantifiable benefits and return on investments through real world case studies, particularly towards CTO types and decision makers. So if that's you, I highly recommend you register using the link down below. How do you build an auto healing tool for playwright tests? Well, you don't have to figure it out because Philip already has. So on this LinkedIn post, Philip demonstrates a new tool he designed to analyze and debug tests. The tool analyzes data from test traces to identify and suggest fixes for common errors. Unlike standard error messages which often lack critical context, this system dives deeper into timing issues, dead clicks, network problems and other potential causes of test failures. So Philip goes over the MCP server he integrated with Curse ide, which provides developers and testers with specific remediation advice where the issue lies within the test code itself itself or the application being tested. And this proactive approach aims to shorten debugging cycles and streamline your testing process. He also goes over the system's ability to diagnose the root causes of test failures rather than merely just indicating failures, which represents a considerable advancements in automation testing capabilities. So definitely a cool case study by Philip and a walkthrough on how he did it. And definitely Check it out. Give him some love on LinkedIn and give him Let me know your thoughts in the comments down below. Also on LinkedIn I found about a new feature about Chrome and it's all about how there's now AI assistance in the Chrome dev tools. And I learned about it from Aaron who posted about this the other day and I never heard of it. So I clicked on the link he posted on LinkedIn and it points to this new feature which allows developers to interact directly with the AI within dev tools, leveraging context specific information from the expected web page. And the AI can answer questions about styling, network requests, source code and performance, offering explanations of potential solutions to debugging challenges. So to get to it, all you need to do is click on Expect it'll bring up the dev tools you're familiar with. If you scroll to the bottom, it has something called New feature, what's new? And to the right of it, it's an AI Assistant tab. When you click on the AI Assistant tab, all you need to do is allow AI assistance and allow it. And once it's enabled, when you click on the AI Assistant tab, it'll give you a bunch of options of what you can do to leverage it. Also, I'm not sure how many people are familiar with this Selenium based framework, but it is now officially part of the Selenium ecosystem. What is it? So wasiq announced a few days ago that the Boyka framework is now officially part of the Selenium ecosystem. We covered the Boycott framework a while ago on the show, but if you missed it, it helps you create highly maintainable automated tests, web API, Android and iOS applications, and for example, use it to automate REST APIs, automate web apps on major browsers, and also automate Android apps on local Android emulators, real devices, cloud providers as well. And if you click on the link where you can see a list of a bunch of awesome frameworks, with Boyka now one of them. So congratulations Wasiq, and thank you for all your contributions to the community. So I know it feels like the new buzzword this year is all about AI agents, but it's something you can't ignore because everyone's jumping in. For example, OpenAI has just released a new tool aimed at simplifying the development of AI agents for businesses. So we're probably going to see a proliferation of this. So these tools part of the new Response API designed to replace the soon to be retired Assistant API. So this API allows businesses to create AI agents capable of performing tasks like web searches, file scanning and website navigation, similar to OpenAI's operations product. And a key component is the Computer Use Agent model, which enables automation of computer task. And also OpenAI has also released an open source agents SDK to facilitate integration and monitoring for those AI agents. So I think this is important that software testers don't overlook AI agents, don't get turned off by the buzzword, just become more familiar with it because I think we're going to see an explosion of these type of tools. You're probably going to have to test them and I think there's going to be a need for testers to focus more on testing the interactions between AI agents and and existing systems and being able to verify the reliability of the AI agents actions and outputs, which I think is a skill that's going to grow more and more in demand as the year goes on. So it's been a while since the Guild has heard from our friend Iran Kinsbruner, so I just wanted to share this with you. He posted a link to a new AI autonomous debugging tool by Light Run. No no. Lighthouse is a developer observability platform and they just designed this tool that's going to help to significantly reduce the time and effort required for software troubleshoot. This new tool automates the root cause analysis process, moving from identifying a problem to implementing a code fix. Pretty wild stuff. The system analyzes, logs, traces and metrics in real time to detect anomalies and predict potential failures, and then correlates events between distributed systems and suggests fixes based on identification models and historical data. And the debugger operates within your ide, streamlining the debugging workflow even more. And the process starts with the developer providing the debugger with issue description. The AI then identifies the relevant code files, suggests troubleshooting steps and root causes, and guides developers in validating these using the light runs debugging actions and the entire process from ticket to fix is substantially automated. And lightrun also claims that this approach dramatically decreases meantime to resolution and enhances software quality. All right, for links that are within value we covered in this news episode headed over to links down below. So that's it for this episode of the Test Skill New Show. I'm Joe A mission to help you succeed in creating end to end full stack pipeline automation awesomeness. As always, test everything and keep the good Cheers.