DEV Community

Cover image for A puzzling and pleasant first experience with Google AI Studio
Phil Eberhardt
Phil Eberhardt

Posted on

A puzzling and pleasant first experience with Google AI Studio

#deved #learngoogleaistudio #ai #gemini

Education Track: Build Apps with Google AI Studio

This post is my submission for DEV Education Track: Build Apps with Google AI Studio.

What I Built

My daughter was doing a puzzle and I thought it would be helpful to have an application where I could get a prompt from my daughter and make a jigsaw overlay on the generated picture. I could then print it out on card stock or something to have some fun in real life.

I started with this prompt:

Please create an app that will generate an image in puzzle pieces based on a user prompt and puzzle piece count

I had another prompt to see if I would get better starting pieces:

Please create an app that will generate an image in jigsaw puzzle pieces based on a user prompt and piece count.

Demo

Screen shot of image prompt and initial puzzle size:

Puzzle generator prompt and size selection

Screen shot of a generated puzzle and the actions you can take:

Image generation on submit of previous picture, includes some action buttons to start again, adjust size, or print.

The AI studio app share as I don't have the funds to deploy anything actively.

My Experience

Overall I enjoyed the AI studio interface and hope to play with it more. Some thoughts:

  1. Starting prompt should be a little more precise. While adding "jigsaw" didn't help the second try (it was still squares), I should have mentioned I wanted something printable so it wouldn't start interactive.

  2. AI can fix bugs when pointed out using natural language. Though sometimes I had to refine my response (like learning better puzzle piece terms for sockets and knobs), it was quick to fix and preview the next iteration.

  3. Seeing the thinking process and explanation of changes is really helpful. After each of my text entries you can see the AI thinking in steps. Generally after it was done you would see bulleted lists/paragraphs saying why it was doing something and explaining some new terms. The way it responded helped me figure out how to approach fixes.

  4. It was weird to see the changes without any manual coding. Still pretty new to this stuff but it was really cool seeing the diffs pointed out and having a two page dynamic web app without me going into any code myself. The downloaded version had the extra setup files in it as well, which didn't clog up my initial editor view.

  5. The AI can suggest prompts for the app. Perhaps this is a form of the phrase, "eating your own dog food". It was fun to ask the AI what puzzles it would suggest. It had three suggestions across a few themes and they all seemed pretty fun.

  6. I was surprised after a few iterations it could get the jigsaw pathing right! There were maybe 5 back and forth type prompts to get it working. I wasn't sure if I was explaining very well. Adjusting based on what AI studio was thinking helped the process along. I really like the setup!

This was my first submission ever so I actually created another post before this one. Overall this was really cool and my first try at using AI to help me build something. It was pretty amazing to have a working client side application that could use Gemini and an image service (Imagen). Please comment if you have any thoughts!

Top comments (0)