The brainstorm buddy

What does this app do?

Our AI-powered issue tree tool is a powerful problem-solving tool that can help you identify and organize key issues related to a particular challenge. This app can assist in structuring your thoughts in a logical way and spark some brainstorming, generating fresh ideas that you may not have considered otherwise. This makes it an excellent tool for both creative and analytical thinking.

Whether you’re working on a complex business strategy question, a local policy issue or a global development challenge, this tool can assist you to approach problems in a logical and thoughtful manner. It won’t give you answers, but will help you think through the questions that you need to answer in order to solve a problem.

This app is most useful when you ask it the same question multiple times. Each time you will get a different answer, and maybe within these answers will be some useful ideas for you to build on.

What do I need to know about the input and the output?

Our AI-powered issue tree tool is incredibly easy to use – all you need to do is input a policy question or statement, and the tool will generate an issue tree with two levels of detail. Typically, the tool will identify 3-5 themes, and 3-5 issues to consider under each theme (but this can vary). You can visualize the results in the app directly, or download the output in a neat and structured excel sheet.

What’s important to remember is that this is a probabilistic tool. This means a number of things: (i) each time you run the model with the same question, you will get a different answer; and (ii) it can make mistakes or produce content that doesn’t make any sense whatsoever. That is unavoidable at this stage, but we are constantly working to improve the quality of the model.

To get the most out of this tool, it’s important to clearly and specifically define the problem or question you want to address. Adding relevant context to your problem statement can also be helpful. To explore different angles and approaches, you can re-run the model multiple times and experiment with slight variations in your problem statement. Using precise and carefully chosen language will also ensure the best results from the model. Please note that at this time, the model works best in English, but you can also use it in different language.

As you use this tool, be sure to respect our terms of use. We have done our best to train the model not produce output that is disrespectful or biased, but unfortunately this is not always possible to control.