The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
A sample LLM evaluation report analyzing AI responses for accuracy, reasoning quality, hallucinations, and failure patterns. Demonstrates structured testing and quality assessment workflows.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Most AI products show you results.
I wanted to show you the process.
So I built MIRROR — a cinematic AI surveillance interface designed entirely in Figma Make.
Instead of static sections and generic cards, every interaction reveals how the system thinks:
• Real-time identity analysis
• Object detection overlays
• Behavioral tracking
• Detection systems and capabilities
• Live subject profiling
• Technical specifications
• Interactive data visualizations
• Hover states, reveals, and system reactions
The goal wasn't to design another dashboard.
The goal was to create an experience that feels like you're inside a classified intelligence system.
Every screen was designed to feel alive.
Every section responds.
Every interaction reveals something new.
Built with Figma Make as part of the Config Makeathon.
Would love to hear what feature or interaction you'd add next.
The level of detail in this is insane. Every section feels like it belongs to the same universe.
I'm building a tool for #ConfigMakeathon and the whole product depends on one AI prompt, which rewrites one message across 8 emotional registers and predicts how the reader will react at each one. Not only what tone was it writen write but how will it land.
So before building any UI, I built a test harness: 5 messages × 8 registers, all outputs in one grid. Run it, read every cell, spot problems before they're in the product. The stress test: "ok" across the full spectrum.
Two rules from the prompt doing most of the work:
1. Every version preserves the exact meaning. Never invent excuses or details not in the original. Only the register changes.
2. Reactions roast the situation, never the sender.
The harness passed 🎉 Now I'm building on a proven prompt instead of crossing my fingers.
Everyone's asking if AI will replace designers.
Wrong question. Ask what AI is built to do.
It takes everything people have already made and hands you the most agreeable version of it. Trained to please the average person, so it always drifts to the middle.
That's the catch. AI nails the stuff most people would nod at.
Taste is the opposite. Picking the thing most people won't, because you know it's right. A machine can't do that. It's got nothing on the line.
Read on Substack
This is the kind of work that inspires others 👏 Very clean, professional, and well presented.
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
MagicPath
The canvas is infinite, and exploration is becoming the workflow. How are you using MagicPath?
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?