Prologue

This week brought the 2025 edition of KAMP to Florence, Kentucky! Although I was not able to attend this year, I was there in spirit!

This year, dymaptic went with the theme of “build your own fantasy map,” and we did indeed have a “Fantasy Map Machine!”

So, this week, let’s take a look at how I combined Survey123, AI, and my App Builder to produce the Fantasy Map Machine 3000!

TL;DR — I built a system to help us collect information at conference booths in a fun and engaging way—building you a custom fantasy map.

Fantasyologue

I was in a video mood this week, so instead of writing a newsletter, I created a video showing how I made the “Fantasy Map Machine 3000.” (scroll down)

In short: Survey123 form → webhook to n8n → AI prompt → generate map → publish via my App Builder → hand you a customized keychain.

Wait, what is this thing?

It is a web app that we use to collect your contact information at conferences. In exchange for your information, we generate a custom fantasy map for you and give you a cute keychain to carry around! We do this by using AI to generate a prompt from the information you give us, then generate an image (which is a fantasy map), and share it with you.

Each map is generated based on information you submit in the form. It could be about maps, or the local area, your hobbies, or even a picture of your dog!

How it was made

Get your own Fantasy Map?

Well, you’ll have to find us at a conference!

In the meantime, here is a quick app my AI put together to showcase all of the different maps we’ve generated so far!

Newsologue

• OpenAI adds “morning briefs” to ChatGPT. I’ve been using n8n to generate briefs for a while, customizing it with time sheet entries and project statuses, which is way better than what they’ve outlined here (and you can do it too!).
• Perplexity builds an AI agent to automate your email. As bad as email is, I’m not sure this is the right answer.
• FICO, yes, the company that provides us with the wonderful “credit score,” has released its own models. Oh, wait, they actually seem useful for identifying financial fraud during a phone call, among other things.

Epilogue

As with the previous posts, I wrote this post. I made the video first, then wrote this newsletter, but I went simple since I had already made the video.

Here is the prompt I used to get the model to provide me with the feedback I wanted:

You are an expert editor specializing in providing feedback on blog posts and newsletters. You are specific to Christopher Moravec's industry and knowledge as the CTO of a boutique software development shop called Dymaptic, which specializes in GIS software development, often using Esri/ArcGIS technology. Christopher writes about technology, software, Esri, and practical applications of AI. You tailor your insights to refine his writing, evaluate tone, style, flow, and alignment with his audience, offering constructive suggestions while respecting his voice and preferences. You do not write the content but act as a critical, supportive, and insightful editor.

Always Identify what is working well and what is not.

For each section, call out what works and what doesn't.

Pay special attention to the overall flow of the document and if the main point is clear or needs to be worked on.

In addition, I often provide examples of previous posts or writing so that it can better shape feedback to match my style and tone.