Explore & Learn

Get Your Hands On Automation & AI at Bot Games Season 4 AI Edition - Challenge #2

Related products: AI & ML
Get Your Hands On Automation & AI at Bot Games Season 4 AI Edition - Challenge #2

You’ve Arrived at Bot Games Season 4 - AI Edition!


Welcome to the first challenge of Bot Games Season 4 - AI Edition! Who doesn’t love some friendly competition? We're challenging you to showcase not only your automation building abilities, but also your proficiency in crafting well-designed prompts of generative AI models that elicit the desired responses in the appropriate format. The spotlight is on the potential of Generative AI, and we're excited to witness how you can harness that power to develop integrated automation solutions. So get ready to flex your creative muscles and show us what you've got.

New to Bot Games? Bot Games is a global competition that challenges developers to build automations that can solve realistic business challenges in free-to-use, scored, and timed environments. Head to our Bot Games HQ here for more information.

Challenge #2 Introduction


Glad to see you back for the second challenge of Bot Games Season 4 - AI Edition! Our objective this time is to showcase how a Generative AI model can enhance and improve existing data in the manufacturing industry. It's important to note that Generative AI isn't limited to solving complex problems, but can also handle simple and routine tasks with ease.

For more details and tips to get started, visit the Challenge #2 Use Case page.

Challenge #2 Objective


A manufacturing company, Genexit International, has received a list of orders and intends to ship them with tracking numbers. For each PO listed on the challenge page, look up the corresponding information in the ProcureEase purchase order lookup application and generate the tracking number using the ShipGlobe Tracking Number Generator application. Then select the Shipping Type (based on the rules below) and submit the form.

Shipping Type should be determined based on the following criteria: for orders with a value of $300 or less, Ground Shipping should be chosen, and for orders with a value of $600 or greater, Express Plus should be selected. Otherwise, Express should be the default option.



Use the Generative AI provider of your choice (ChatGPT, for example) to get the full state name for the state code mentioned in the ProcureEase purchase order lookup application. For example, if the state code for PO number 99-771-9626 is TX, pass the state code TX to ChatGPT and ask for the full state name. Then, parse the response from the model and use the state name in the ShipGlobe tracking number generator application to proceed with generating the tracking number.

Challenge #2 Tips


  • ChatGPT can respond back in different formats. Try phrasing prompts in different ways to see how the response varies. Be specific about the values for which you are looking and the format in which you want the response.
  • You have the option to either get the full state names for all states in the US from ChatGPT at once or to invoke ChatGPT for each state code associated with a PO. The choice is yours!


Challenge #2 Solution Tutorial


While Generative AI is often touted as a solution for complex problems, its potential goes far beyond that. The technology has shown great promise in simplifying routine tasks, streamlining processes, and improving efficiency. In this use case, we can envision how we could use data from the model to fix/perfect the data we already have. By using Generative AI for such routine operations, businesses can focus on other aspects of their operations, such as strategy and innovation.

As AI technology continues to evolve, we can expect to see even more applications of Generative AI to optimize workflows, reduce errors, and drive greater success. By embracing these advancements, businesses can stay ahead of the curve and continue to innovate and grow.

  • Using the cutting-edge OpenAI Generative AI Package brings the power of OpenAI's advanced generative AI technology directly to the Automation Success Platform. It functions with GPT-4, ChatGPT-3.5 Turbo, and GPT-3 models with both OpenAI and Microsoft Azure service providers. Check out this link to learn more about this package and its capabilities.

The process of creating an automation can be an insightful learning experience. You can experiment with various packages or actions to complete the task and observe how these changes affect the automation's processing time, accuracy, and stability. Finding innovative ways to solve the same problem can also lead to greater efficiency and productivity in your work. Moreover, experimenting with different approaches can help you develop a deeper understanding of the tools and technologies with which you are working.

View the full solution tutorial video here and get more details on the various packages and approaches that can be utilized to solve this challenge.

Be the first to reply!