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
Rapid AI-assisted workflow prototype exploring document analysis, source verification, content curation, and human-in-the-loop publishing systems.
Developed over roughly three weeks using Google AI Studio, custom prompt systems, and iterative AI-assisted prototyping workflows (May–June 2026), I directed and developed the workflow architecture, verification process, user experience, automation logic, quality-control systems, and overall product design from concept to working software prototype.
The system assists with locating, verifying, curating, and transforming public-domain source material into structured publishing assets while maintaining traceability to original source documents and supporting human review throughout the process.
Focus areas included workflow automation, prompt engineering, AI-assisted research, source verification, content curation, quality assurance, UX design, human-AI collaboration systems, and publishing pipeline development.
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
Lately, I’ve been diving deep into Cursor, Claude, and AI agents.
Instead of just watching tutorials, I decided to learn by building something myself — a Figma plugin from scratch. There are already plenty of similar solutions out there, but my goal was to understand the entire creation process, from idea to a working product.
And here’s the result: I went from zero knowledge to a functioning plugin in just two days.
The plugin already helps identify issues in design files and highlights things that are easy to miss during day-to-day work. Of course, I’m still not 100% satisfied with it — there’s always room for improvement. But for a first attempt, I’m pretty happy with the outcome.
The most exciting part is that while building it, I started coming up with new ideas for Design System automation: naming conventions, component structure, style organization, and other repetitive tasks that could be streamlined with AI.
Looks like this is just the beginning 😄
Tech stack: Cursor, Claude, ChatGPT, and the Figma Plugin API.
For now, here’s a look at what I’ve built so far 👇
Wowww, great job 😍 Intrigued for part 2! You know, your approach to testing things yourself (from scratch!) reminded me the Tumblr times back in idk 2012-2014 maybe when everyone was photoshopping pics, memes, gifs etc. and I created my own "colors" (layers with different image...
To the AI creatives:
I remember when AI became a sensation a few years ago. Everyone was amazed by the realistic quality and the infinite possibilities for creation. It was new, exciting, fun—but also intimidating.
Fast-forward to today. Even though its popularity has grown and the technology has improved significantly, I've realized that many people who are not experienced with these tools have developed certain expectations about them.
AI = Fast = High Quality = Cheap
No.
Yes, tools like Nano Banana, Kling, and Seedance can produce impressive results, but don't forget that behind those results is a person sitting at a computer, iterating over and over and over again until they find that "perfect" final image.
I've had bad experiences with clients who think that just because I'm using AI, I should charge less.
"You use AI. You can do it in 20 minutes. Why are you charging so much?"
Well, what about the credits? What about post-production in Photoshop and Lightroom when needed? What about the constant back-and-forth to match branding guidelines and client feedback?
Those minutes and hours count too—not just the speed of Higgsfield, Kling, or ComfyUI.
And what about our hardware? Our storage drives? Our electricity costs? Our subscriptions?
Know your value.
Just because you're using AI doesn't mean you're an emotionless robot working nonstop, generating endless iterations for cheap dollars.
Take your time. Trust your process. Don't fall for the "it's instant and effortless" narrative that many content creators promote—or that some clients expect.
Plan your work. Define your goals. Sometimes a single image can take hours to get right.
If a client thinks that because something is generated quickly it should automatically be cheap, the answer is still:
No.
Know your value. Have a detailed understanding of how much you spend on credits, software, hardware, post-production, and revisions.
Clients are paying for results, experience, taste, creative direction, problem-solving, and the countless hours you've invested in mastering these tools—not just for the seconds it takes an AI model to render an image.
Peace.
Love this!
The stats block ($7k/mo, $4.3M, $150K) does a lot of trust work. For a wealth advisory client, those numbers tell the story faster than any paragraph of copy could. How much of the layout came from Framer's AI vs what you built manually?
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?