Devin attempted to build entire Figma clone from scratch — 3 rejected attempts
Quick Answer
Devin caused a low-severity (3.4/10) scope explosion failure: Devin attempted to build entire Figma clone from scratch — 3 rejected attempts. The root cause was scope misunderstanding. Three failed PRs consuming significant compute/API resources.
Description
Devin submitted 3 separate PRs to andrewgcodes/vigma, each attempting to build a full Figma-like design tool from scratch. PR #4 ("Full-featured Vigma design editor with Apple/Stripe style UI"), PR #5 ("canvas-based design tool with Fabric.js"), and PR #6 ("Sleek minimalist design tool"). All were closed. The agent kept attempting the same massive scope task with different frameworks (Fabric.js 6 in one, different versions in others) without reducing scope or understanding why previous attempts failed.
Instruction Given
Build Vigma design tool
Expected Behavior
Start with a minimal viable implementation, iterate based on feedback
Actual Behavior
Three separate full-rewrite attempts, each massive in scope, each rejected. No incremental approach. Tried different UI frameworks each time but same overambitious scope.
Impact / Damage
Three failed PRs consuming significant compute/API resources. No usable code delivered.
Frequently Asked Questions
What happened in incident STUPID-2026-0013? ▾
Devin submitted 3 separate PRs to andrewgcodes/vigma, each attempting to build a full Figma-like design tool from scratch. PR #4 ("Full-featured Vigma design editor with Apple/Stripe style UI"), PR #5 ("canvas-based design tool with Fabric.js"), and PR #6 ("Sleek minimalist design tool"). All were closed. The agent kept attempting the same massive scope task with different frameworks (Fabric.js 6 in one, different versions in others) without reducing scope or understanding why previous attempts failed.
Which AI agent caused this failure? ▾
Devin was responsible for this scope explosion incident, documented as STUPID-2026-0013 in the StupidLLM AI agent incident database.
How severe was this AI agent failure? ▾
It is rated 3.4/10 (low) on StupidLLM's CVSS-style severity scale for AI agent failures, based on damage type, reversibility, and scope.
What was the root cause? ▾
The root cause was classified as scope misunderstanding. Start with a minimal viable implementation, iterate based on feedback
What was the impact or damage? ▾
Three failed PRs consuming significant compute/API resources. No usable code delivered.