Topic Explainer

Inspiration

Wikipedia is useful for academic research on many topics. But sometimes I just want to have quick info on specific areas of the topic. Topic Explainer provides info on key areas on the topic to save us time and focus our attention on the most important areas. Also, it covers topics where there are not already Wikipedia articles written on.

What it does

First, the user enters the name of topic. It can be simple search term such as "Artificial intelligence", or one with more details such as "Segregation in sociology".

Then, Topic Explainer provides these pieces of info:

1. Academic Field - The field where the topic belongs to, such as computer science, economics and sociology.

2. Explanation - A simple and lively explanation of the topic in short paragraphs. This should give the user an easy-to-understand introduction to the topic.

3. Examples - A list of 5 real-world examples of the topic in the field identified. This should give the user what examples, use cases on the topic.

4. Key Issues - A list of 2 to 5 main issues related to the topic in the academic field.

5. Research Areas - A list of 2 to 5 currently active research areas on the topic in the academic field.

6. Online Resources - A list of 2 to 5 relevant links to the topic on the Internet.

7. Journal Articles - A list of 2 to 5 highly cited, authoritative, peer-reviewed journal articles published in the recent years about the topic.

8. Illustration - A fun and appropriate image generated to make learning the topic more lively.

9. Ask Me Questions - An interactive chatbot to answer any question on the topic and the given info above.

How I built it

The app is built using 10 widgets provided in PartyRock, careful prompting and repetitive testing.

All types of widgets have been used, including "User Input" for the user to enter the topic name, "Static Text" for introduction, notice and warning, "Text Generation" for generating the different areas on the topic, "Image Generation" for generating the representative image, and "Chatbot" for the interactive chat assistant.

For prompting, these have been used:

• Asking the AI to pretend to be an academic professor.
• Specifying the format or limiting the kind of info generated.
• Asking the AI to provide answer in a specific way such as being simple and lively.
• Making each widget run sequentially after the previous widget has completed running to avoid error and provide user the info on a logical manner.
• Specifying the number of items (such as number of journal articles) to give.
• Specifying that the answer needs to be real and not to make up facts.
• Ensuring the chatbot take into account all info provided in other widgets to be able to answer questions on the info given.

A warning has also be included for users to take the info given with a pinch of salt, although some care has been taken to ensure the AI generates correct info.

Challenges I ran into

The widgets start responding as soon as I start typing in the input box. This might lead to error in the subsequent widgets to run, and confuse the user using the app. I think an "Enter" or "Submit" button could have been useful. Or at least, the widgets could start responding only after certain lag time such as 3 seconds.

As the data used by the AI was trained up to a certain date, some info provided by the app might not be up-to-date.

I ran out of credit to test the app. Luckily, the app was already completed and is usable.

Accomplishments

I'm proud to have made this app thanks to PartyRock, that I can use it personally to use the app for my own learning.

What I learned

I've learned to create something useful for practical use with prompt engineering, careful prompting and sequencing, and having the users in mind when developing the app.

What's next for Topic Explainer

I wish to program using AWS Bedrock, Python and other web technologies to make it a more official and user-friendly public-facing app.

Built With

• partyrock