"One of my favorite uses of AI is to take abstract data and write a human readable form of it. Now to be clear, this is not something you need AI for. Given that you know the shape of your data, you can create your own summary using hard-coded rules about what values to show, how to present them, and so forth. What I like about the Gen AI use-case for this is the amount of randomness and creativity you get in the responses. In the past I've done this with weather forecasts and chart data, but today I thought I'd try something different - monsters."
"A lot of Dungeons and Dragons content is available, legally even, online in API and JSON formats. The D&D 5e API includes information on all aspects of the game, from classes to spells to monsters. While the API is handy, I knew I wanted the raw data as is so I headed over to the repo and grabbed the raw monsters json file. This JSON file contains information on every known monster. Here's an example, an you can see it is quite extensive (I won't be offended if you just skim this):"
A demo loads a large monsters JSON file (around one megabyte) and offers a simple UI to interact with the data. The interface allows selection of a random monster and display of the raw JSON or conversion into a human-readable paragraph. The source data came from a D&D 5e repository containing comprehensive monster information. The workflow emphasizes that summaries can be produced with hard-coded rules but highlights Gen AI for added randomness and creativity. The demo uses Chrome AI and notes the Prompt API was behind a flag at the time of development. Example HTML is included for implementation.
Read at Raymondcamden
Unable to calculate read time
Collection
[
|
...
]