Zoomable app architecture canvas
- Views
- 192K
- Likes
- 1.6K
- Replies
- 87
- Saves
- 3.2K
An interactive, zoomable visual map of an app's architecture (signup, payment, file upload flow) was generated by giving Claude Opus 5.5 a single prompt to analyze the existing codebase.
Full prompt1,087 chars
I have a weird task for you. I want you to look at the app and create, for lack of a better word, a canvas that I can zoom in and zoom out and move around to see how our architecture actually works. A lot has changed, and I'm starting to lose an overview of everything that we're doing, especially with Model and Convex. I want you to map out in a visual way what happens when a user signs up, pays, or gets a guest pass, and then they upload a file. What happens? We create, for example, right now. That's one of the things that I really want to understand. Right now, we're still creating a chat and a project, but the chats are actually independent, I believe, and the projects, I don't even know how the fuck that works. That's already where it starts. A file is being uploaded, and then that file is being put somewhere into R2 storage, and then some modal workers are doing some things. There's a modal app, or one modal worker, but that has multiple apps. I don't really understand how that works either. I really want you to have a visualization of how this actually all works.
Source: the creator's reply under the post. Kept in its original language, unedited.
Want more prompts like this one?
Get the 50 most-viewed Claude 5.5 video prompts on one page: the full original text, the creator and the post it came from. We'll only email you when there's a new prompt worth trying. Unsubscribe anytime.
Needs your own reference assets: besides the text prompt, the creator supplied images, video, audio, documents or a codebase, which are not hosted here. The prompt alone will not reproduce the result.
Original post: https://x.com/robinebers/status/2105309987983745060
All works are open data at GitHub · awesome-opus-5.5-video.
Model attribution is as stated by the creator and was not independently reproduced. View counts are a snapshot from 2026-11-19. The work belongs to its creator; DM @GoSailGlobal on X for corrections or removal.
More explainers
0:32Interactive camera focus lens lab
3.6M views
0:35Interactive Raptor 3 rocket engine explainer
1.2M views
5:15AI documentary about superintelligence
916.5K views
0:56Pixel art neural network training animation
579K views
3:09Human progress to future animated film
435.6K views
4:21Hour-by-hour simulation of Singapore occupying Batam
420.4K views
Related articles
DeepLearning.AI Complete Course Guide: 120 Courses, Taught by the Authors Themselves — 6 Goal-Based Learning Paths
DeepLearning.AI now has 120 courses — more than the previous eight major tech companies combined. What really sets it apart, though, is something no one else can offer: the courses are taught directly by the people who built the models and tools. This guide breaks down course selections across 6 goal-based learning paths.
The Complete Map of Free AI Learning: 10 Official Platforms, $0 Total Cost
Anthropic, OpenAI, Google, NVIDIA, Microsoft, AWS, Meta, IBM, DeepLearning.AI, Hugging Face — every official AI course from all 10 platforms is free. This is the master index: one comparison table + learning paths by role.
Microsoft Learn AI Certifications: The Big Tech Company That Gives Out Certs Most Generously — One Skill, One Badge
Microsoft is the most cert-friendly major tech company in the AI space — one skill gets you one certificate. The Microsoft Learn AI framework has four tiers, but most people only need the first two. This post breaks it down tier by tier, with direct official links and tips to avoid common pitfalls.
I Ran Six Experiments on TypeSafe Jev: What It Can and Can't Do
Six experiments, five open-source repos, 210,000 judgments: zero-shot Jev is worth a few hundred labels, but its best role is as a feature, not as a model.