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
Built a deployed AI tool that lets users upload research papers and query them using natural language. RAG pipeline with vector search retrieves precise context-aware answers. Features PDF parsing, AI summaries, topic modeling, and citation extraction. Live on Render.
interesting
Thanks! It was built to make research paper analysis faster with RAG. Happy to share more if you’re working on something similar
That sounds cool — using RAG to speed up research paper analysis is a smart application.
I’m not currently building one, but I can definitely see how combining retrieval with structured insights would make literature review and knowledge extraction much more efficient....
For chunking I used RecursiveCharacterTextSplitter with chunk size 1000 and overlap 200 — this preserves context across chunks well.
For retrieval accuracy, ChromaDB with cosine similarity worked best. I also experimented with MMR (Maximum Marginal Relevance) to reduce redundant...
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
It was 2am, couldn’t sleep, overthinking as usual… and then this idea just hit me 👀
What if you could take any blurry or old photo and turn it into a clean, detailed 4K image?
So I built it.
Been testing it out and honestly… it’s kind of crazy seeing old or low-quality images come back to life like that.
Try it now !! - 4K photo upscaler
Built totally using @Morphic.
Building a Zero-Touch Design Feedback Loop with Slack and the @Paper MCP
What if you never had to manually process a minor design revision again? As designers and developers, we easily waste 30% of our week fulfilling fast client requests—changing button colors, adjusting typography, or tweaking padding. I decided to completely automate this process.
In this project, I engineered an autonomous AI-driven workflow that physically alters native UI designs based on conversational Slack messages, proving the massive potential of the Paper MCP.
✨ The Power of the Paper MCP: Historically, AI agents have struggled to actually "see" or edit design files. By deploying the Paper MCP, I gave a raw Large Language Model the ability to programmatically traverse a 2D design canvas.
The Setup: I design the initial UI (like a Login Page) using Paper and post the screenshot to the client's Slack channel.
The Trigger: The client requests changes natively in Slack by mentioning a custom @DesignBot (e.g., "Make the login button green and change the title to 'Welcome'").
The Execution: Instead of guessing layout geometry, the AI uses the Paper MCP to dynamically query the canvas, isolate the precise target node, and duplicate the master to create a protected variant. It aligns the new design on the canvas grid and updates the styling properties natively.
The Delivery: The MCP server intercepts the final render state and pushes a flawlessly formatted screenshot right back into the Slack thread.
🛠️ Technical Stack Used:
Paper MCP: The absolute core of the project, enabling rigorous JSON-RPC access to native design layers, text bounds, and styling hooks.
Slack Bolt (Socket Mode): For threading logic, instant reaction processing, and conversational memory.
Agentic LLM Engine: Used native OpenAI tool-calling to map the complex MCP schemas directly into the AI’s brain so it never hallucinates commands.
The Result: Clients experience magical, instantaneous visual revisions directly inside their communication channels, while designers and developers win back hours of completely uninterrupted, deep-focus work.
Check out the video demo below to see the AI leverage Paper MCP to parse a layer tree and dynamically manipulate the UI!
This is the kind of workflow that quietly kills 30% of design busywork 👀
🚀 I built a complete school website with just ONE line using Claude AI.
No complex setup. No long prompts.
Just a simple instruction — and the structure was ready.
Here’s what this shows 👇
AI is not replacing developers… it’s upgrading the speed of execution.
But let’s be real —
A generated structure is NOT a high-converting website.
What actually matters:
✔ UX that guides user behavior
✔ Clear content hierarchy
✔ Conversion-focused sections
✔ Real business goals behind the design
That’s where real developers & designers stand out.
AI can generate.
But strategy + experience = results.
I’m now combining AI speed with UX-focused WordPress development to build websites that don’t just look good — but actually bring leads.
If you're a business owner or founder, and your website isn’t converting…
Let’s fix that.
#AI #WebDesign #WordPress #UXDesign #ConversionDesign #Freelance #ClaudeAI
Really like how clean and engaging this feels. If someone wanted to reach this level, what would you say makes the biggest difference in your process?
Trending
Runway
AI video generation is exploding. What are you dreaming up in Runway?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
portfolioreview
The best portfolios tell a story, not just show a grid. Share yours for feedback.
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?