AWS PartyRock

AWS is recently hosted a hackathon (ended on March 11, 2024), where participants were challenged to create an AI app using the PartyRock platform. Essentially, this involves leveraging AWS BedRock technology and offers a fun opportunity to explore AWS's generative AI services.

If you're familiar with hackathons, this one follows the same format. Contestants will compete in various categories and have the chance to win CASH prizes. So, if a hackathon has a specific format, can we use AI to help us win?

Hackathon Hack a.k.a HackaThong

My idea is straightforward: you give the user inputs that I'll use as context for the generative AI to create a winning suggestion. Instead of making this specific to just the AWS PartyRock competition, I'll make it more generic so that it can be reused.

Why HackaThong? I'm Australian, and we refer to rubber-style casual footwear, similar to sandals, as thongs or pluggers.

What do hackathons have in common?

1. Summary of the hackathon

2. Terms and conditions

3. Criteria for judging

4. Examples (often provided to inspire creativity)

This should give enough context for our AI to offer suggestions, but what about the output?

1. A winning idea

2. A catchy, unique name

3. Some artwork to help visualize the idea

4. A written summary describing the app

5. An application to the competition that we can use as a starting point

Time to build a thing

I'm going to quickly explain how I built this with PartyRock. But first, I want to recommend a few articles that cover this topic in more detail (and better) than I will:

1. https://community.aws/tags/partyrock-hackathon

   1. All of the folks who decided to write about PartyRock on community.aws

2. https://community.aws/content/2bpGEn7TeXH4XkL0Z4j4eSumK0v/master-prompt-engineering-elevate-ai-with-claude-partyrock

   1. By Viktoria Semaan, great write up, goes into models, prompt engineering

I'm going to start with an empty app and just start adding widgets:

Instead of starting with an empty app you can write a description and PartyRock will have a crack at creating the app you might need.

Based on what we know, we need a lot of input from the user. So, for the first widgets, we'll create several user input types:

Hopefully this is straightforward, title, placeholders etc.

The first couple of user input widgets are straightforward: they're simple text fields where the user can provide context about what the AI needs to do. Very little setup is needed—just name it and hit save.

This is where the fun starts. The next few widgets will use the inputs from above to perform the AI magic. We then create an AI-Powered widget and link it to the previous input widgets.

A few things to note:

1. You can change the model based on your requirements, there is a brief description of the models here

2. You design your prompt

   1. We are giving the AI some context

   2. We are giving the AI some input from our text (more context) by referencing the input using @widget0 (or whatever the name is)

From this point, we continue the process, creating more widgets until the app looks something like what we intended to develop.

Let's talk about the fails

• The AI kept suggesting the same thing. For example, it would suggest a cooking app every time. I had to reword the prompt to resolve this, and even so, it can provide things that are pretty similar.

• There is a word limit. Not too surprising. The terms and conditions are super long (expected), so there is a point in the T&Cs that I truncate to accept most of the content.

• Initially, regenerating ideas was a bit dumb because I'd simply update the inputs. But, <insert facepalm> there is a little refresh button on the widget to resolve this.

Try it out

You can try out my app on AWS Party Rock, it's a little bit of fun. Your mileage may vary on how useful it is to win a hackathon with, but hopefully, you can see some potential in generative AI.

The reasons

I've been running my own site on AWS for some time. It's been mostly fine, and it's pretty cheap (static s3 site), which is great. However, managing the infrastructure and creating new content takes a bit more time. It's not a huge issue, but with the recent updates to forestry.io and the switch to tinaCMS, I'm a bit over it.

As a member of the AWS Community Builders, there has been some discussion about the new AWS community site. During these discussions, Hashnode was mentioned, so I decided to check it out.

Hashnode

I've previously used Ghost CMS, which is good, but I chose to host my own to save money and take a more hands-on approach. After doing this for over 12 months, I'm now switching to Hashnode. This is a fully managed site without any infrastructure for me to manage, but it does come with a cost. I decided to opt for the premium site option (thanks to a sweet deal).

As you may have noticed, I've also registered a new domain name. Most of the content on my other site is about solving problems and sharing my thoughts. This site will be pretty much the same (or maybe not, I'm not sure yet 😂).

More soon

I won't be migrating any of the content over, and I won't be taking it down either; based on the stats, it's still helping folks. My main focus with this site will be broader engineering "challenges" (fails), not limited to cloud. I'll be looking to tweak the look and feel (no idea how). That's it, short and sweet. More content is on the way. This new platform should make it easier for me to publish content, so I'm hoping 🤞 to share more soon. If you want to be notified, you can subscribe? Or not? 🤷.