Challenge #3 - Automation Resiliency
We're excited to present the third and final challenge of Bot Games Season 4. Our aim in this challenge is to showcase how a Generative AI model can enhance automation resilience. When target applications are updated, the object paths for elements may change, requiring updates to the corresponding automations. By utilizing a Generative AI provider like ChatGPT (or any other provider of your choosing), we can input the source code of a web page and request object paths for all the necessary elements. These paths can then be used to automate interactions with the web page.
OpenAI Generative AI package is available in Bot Store and you can read the included documentation or check out our quickstart video showing the full setup process. If you are using your own enterprise version of Control Room, you can download the OpenAI Generative AI package from the Bot Store and import it. If you are using the Community edition, it is already pre-loaded.
A financial services company called Spacely wants to add details of its corporate customers to a new Saas-based customer relationship management system (CRM). Because it's an application they subscribe to and don't own, updates to the application can come without warning - make automating data entry challenging.
Download the spreadsheet from the challenge page and enter each customer's information. Click 'Add' after entering each customer's details to commit them to the CRM and 'Submit' once all customers have been entered. Be careful, sometimes their CRM intake interface changes without warning!
Note: Like experimenting with any emerging technology, you may encounter a few things that feel wonky in these Generative AI challenges. Part of the "challenge" in this case is learning how to effectively roll with it, write better prompts, and solve interesting problems using the newest and best of AI + automation.
Use Generative AI to keep your automation running! Identify the object path for each element as changes to the application occur to ensure your automation can continue entering the corresponding data.
Ready to get started? The Automation Resiliency Challenge is ready... we hope that you are!
Sharing Your Results
Once you’ve successfully completed the challenge, share a screenshot of your results on any social media platform using the hashtag #BotGames and tag 3 other RPA developers who you’d like to challenge to complete this exercise. We want to celebrate your accomplishment as well, so our team will be looking for individuals who share their results on social media (and tag/challenge others) to reward them with limited edition Bot Games swag.
Upon completing this challenge, you will be able to download a certificate of completion ( https://developer.automationanywhere.com/botgames/validate ). In addition, if you have successfully completed all three challenges this season, you can download a Trifecta certificate by using this URL. ( developer.automationanywhere.com/botgames/champion ).
Please share your feedback as well. We want to hear what you enjoyed and what frustrated you about this challenge. Share some tips with your fellow developers and help us build a stronger community!
Generative AI can play a crucial role in improving automation resiliency by identifying new object paths for elements in a webpage whenever there is an application update. This can be achieved by sharing the webpage source code and asking the model to recognize and identify the object path for different webpage elements such as buttons, links, forms, etc. By automating this process, Generative AI can help ensure that the automations continue to function as intended, even in the face of application updates that might otherwise cause them to fail.
As AI technology improves, we will see more ways to use Generative AI to improve our work. This can help us do things faster, make things easier, and be more productive.
Unlock all Bot Games Season 4 challenges and resources - visit our Bot Games Season 4 HQ today!
Completed Bot Game Season 4 RESILIENCY CHALLENGE
1. 90% of the whole process depends on prompt value which you are giving to chatgpt . So spend some time playing around the chatgpt with various prompts .
2. Always consider process reliability is greater than the execution speed.
3. Pass the filtered HTML code to chatgpt or else, you wont be getting response from chatgpt
4. find out a unique value to pass it as dynamic xpath to set the values - in my case, I have used 'tabindex' id to set the values.
5. Still, if you are getting a combination of responses from chatgpt. We can use logical operator 'or' in the dynamic xpath . So that if either of the value is matched. then it sets the value.
Tips: Web page ID, name, class are changing but label is common everytime
Use chatgpt to generate dynamic xpath for label
Give HTML source code to GPT for better responses.