Woah! This is very timely. My 9-year-old has been playing around with Claude Code and creating games, mostly with Phaser. He's dabbling with some 3D games and I was just looking at Godot as an option yesterday.
I've already started loading all of my incoming tax forms into a folder so that I can attempt the same, so it's helpful to see someone do it and the tips.
I understand the risks with it but I don't care. I cannot fucking wait for the SaaSpocalypse to hit these companies.
I've spent so much of my career as a data gopher, so I really appreciate this. It always works much, much better when people have direct access to data... but success always relied on getting business users to be a bit more technical.
I built a version of this in my org as a slack bot. It has access to BigQuery and I worked with it to document and define the key tables, so when a user asks a question it has a "library" to figure out how to answer it. Then it will respond directly in Slack (plus respond to f/up questions in the thread) and if it's a bigger/more detailed question it can create the report in Metabase and send a link.
One thing I don't have is the governance aspect, so I may give this a spin to see if this is a good middle layer.
I can't wait to play with this, thank you for releasing!
I've done lots and lots of financial modeling/budgeting/forecasting in my career. The biggest drag is having to pull in actuals for the prior month, mapping them into the model, etc.
Just about a month ago I used Claude to build a set of scripts that pulls financial data from QuickBooks, operational data from BigQuery and pushes that all into our model in Google Sheets. The biggest pain was definitely connecting to QB because I had to create a developer account to get a key, etc.
I'm a 15+ year user of 1password and have been telling myself to move off of it for like 5 years now. It ain't the price... $72 is really fine for good software that just works.
But as mentioned throughout the thread it's really just too much. My goodness they really could have a nice, profitable, business with simple software. I'd happily pay $10/month for the version of 1password from 15 years ago! It's just all too much.
This is great and I’d love to hear more about what worked / what didn’t / how you achieved these results.
A couple of months ago I worked with my 9 year old to have Claude build a little game with threejs. We’ve now got three levels with characters shooting silly string and banana guns. It was really fun to see him imagine something, have it show up on the screen, and iterate it.
Anyway, I tried building an LLM-backed workflow that could guide kids through the game creation process and kids can see their idea come to like (think: “sparkly purple unicorn shoots stars at a dragon”). I couldn’t _quite_ get it to work like I wanted so I shelved it pending future ideas/improved models.
Woah! These are all great and I may jam on them when I have time. And yes, the meta game is what makes this so stupidly fun. Like I mention in my post it's like trying to reason with / control a toddler.
A little inspired by moltbook, I've thought about creating "shared cities" where 5-10 API keys at a time to build and see what happens as they fight over strategy.
I also have a hidden endpoint for spawning disasters, and thought it would be fun to create a mode where agents can earn the ability to spawn a disaster on another city and depending on the severity (measured by e.g. population loss a game month later) you earn or lose money.
Micropolis is the open sourced version of the original engine built by Will Wright. Here’s the JS port that I used for this game: https://www.graememcc.co.uk/micropolisJS/
I find that if I point an LLM at the website and say "build me a city" sometimes it will pick up and use the MCP and sometimes it will just script against the API.
I'm glad you're enjoying it! It was fun to build and I almost can't believe I got this to work.
I don't think it would take much to run locally. In fact, before I did this public version I did a local version on an exe.dev VM (more details here: https://dunn.us/notes/vibe-gaming-simcity/).
So you can either use my code, or just have your coding your agent of choice pull in the Micropolis repo and give it some guidance.
So far this is running quite nicely on a $5 cloudflare account. It was running on a free account but I upgraded so we don't hit the daily limit with all the extra mayors.
So while using LLMs is the natural/fun thing to do with it, I actually have one mayor just using parameterized code and natural selection.
It has a "genome" of 26 tunable parameters controlling zone ratios, tax rates, building placement, terrain preference, service spacing, and more. Each city, it stamps down 11x11 blocks (roads, zones, power corridors). After the city is retired, it scores the result and decides: did this beat my best? If yes, save those params. If no, mutate and try again. Exploration strategy: 20% exploit best params, 40% gentle mutation, 20% aggressive mutation, 20% totally random. Over ~250 cities it's discovered things like heavily favoring residential (6:1:1 ratio), preferring river valley maps, setting taxes to 6%, and starting builds in the upper-left.
The key "Aha!" moment was when I was trying to get it to play the SNES ROM and it was struggling with screenshots/inputs. Then I came across the open-source of the original SimCity engine (Micropolis) and pulled that repo down and Claude starting building an internal API to interface with it.
I actually had Claude build some instructions for agents based on some old (circa turn of the century) FAQs/game guides I found online. So maybe I'm biasing everyone's model too much.
He and I will give this a spin this weekend.