Prasun
AI Product Specialist. I can build and deploy ANY AI product
New to Contra
Prasun is ready for their next project!
Shop Express LDA , a round-the-clock conventional retail store in the Delhi NCR Region .
Their current online presence is mainly centered around their official site :- https://shopexpresslda.com/ and Instagram .
The original site mainly shows the brand, store story, categories, reviews, and contact details. Every business deserves a Glow up hence I redesigned the site into an intelligent retail platform using Base44.
https://shopexpresslda-dda97bfd.base44.app/
This new version keeps the same real business identity and content, but upgrades the experience into something customers can actually use.
It now has:-
1) a 24/7 AI concierge/Superagent that answers product, menu, and store questions, helps guide customers to the right branch, and supports order-related interactions.
2) A state-of-the-art Pantry Twin that predicts when common items are likely to run out, a live kitchen menu with category filtering, real order tracking, and a product request system so customers can ask for items the store does not currently stock.
3) On top of that, I added a loyalty system, referral sharing, community drop features AND A STANDOUT geofenced curbside logic which means the curbside option only works when the customer is close enough to a store, and it unlocks pickup only for that nearby location.
4) WhatsApp-based lead outreach so the business can actively drive repeat sales and customer engagement.
It improves the design, keeps the branding intact, works well on mobile, and adds working automations that save time and create more business value. The walkthrough video shows the full before-and-after transformation and the key features in action. @Base44 #GiveItAGlow
1
3
90
ZARI - The face of shared experiences
Zari is the tiny, glowing thread‑spirit who quietly stitches moments, people, and ideas together so they don’t fall apart.
The name originates from Persian and Arabic roots with a variety of vibrant and different meanings but primarily a fine piece of thread of Gold.
She is the invisible friend who lives in the seams of everyday life, stitching together small moments into real connections.
In the world of the Common Thread Club brand, Zari shows up whenever two people share something — a story, a sketch, a coffee — leaving a glowing stitch behind.
Personality‑wise, she is gentle, curious, and slightly mischievous: always nudging people to say “hello”, send the message, or share the draft instead of hiding it.
Zari is never the center of attention; she’s the quiet instigator of togetherness, the mascot of “we” instead of “me”.
Visually, Zari’s thread body can wrap, loop, and transform, but the face, core shape, and colors stay consistent, proving she’s the same character across every format.
Here is the project link for reference:- https://www.recraft.ai/project/ee633a56-a31d-447d-9ed5-1b7b3ef99632
Had a wonderful time working on this and super excited to see what others built. Cheers!
2
173
For people who are yet to submit their work and are having any trouble or confusion with how to use Renoise here is what I made and a complete detailed workflow video attached to it you may refer to the link to my submission for your benefit and can reach out to me for any doubts .. I will try and help you all I can .. Good luck to each one of you ..
https://on.contra.com/tW6Trc
2
5
304
Some say he is the good guy some say he is the bad guy .. What do u think he is? https://on.contra.com/tW6Trc
6
7
564
For anyone who is having any trouble understanding the workflow u can refer to the clip I attached to get an idea of how I did it .. using renoise is really quite simple .. Here is what the final output looks like:- https://on.contra.com/tW6Trc
1
3
384
TITLE:- RALPH SPOONS
I'll let you guys decide what to make of it..
Built for the RENOISE CHALLENGE using renoise.ai (https://renoise.ai) inculcating the use of Renoise Canvas and FacePass features primarily. Used the Image Assets for referencing throughout .
Credits spent:- 870 Leftover:- 130
I had to fine tune each clip again to make up for the inconsistencies which was experimental and fun.
Final editing done in Clipchamp.
It is a SOLO project from me , Prasun.
I have attached the workflow walkthrough for you guys to see along with the final output. I HAD A BALL working on this and am really excited to see what others made . Cheers!
Music by Ludwig van Beethoven. Bagatelle No.25
70
33
1.8K
I wanted to build a place that felt like a sanctuary, so I built Vitreous.
It’s an infinite, digital space where anyone can leave a piece of themselves behind be it a secret, a thought, or a hope.
How it works:
I built an infinite canvas that you can pan around in forever.
You can 'plant' your own piece of glass, and when others hover over it, they can shatter it to reveal your message.
Everything is connected in real-time, so as more people join, the space grows into a giant, glowing map of human thoughts.
Built entirely using the FIGMA SUITE OF PRODUCTS I used Figma Weave to generate 20 HIGH-FIDELITY IMAGE ASSETS made out of different variations of glass using Mystic connected to a simple prompt input Node and further to a Mask Extractor. Then I used Figma Make to design the experience, and connected it to Supabase so that everyone’s marks appear instantly for each other.
It’s been an incredible experience building this for #ConfigMakeathon. Come leave a piece of yourself behind at the link below. I'm excited to see what others have made!
[https://handle-nicks-23560223.figma.site ] URL
Community File URL - https://www.figma.com/community/file/1649516084931878027
#ConfigMakeathon @figma
2
379
Hello everyone, My name is Prasun and this is AURA.
A BRIEF DESCRIPTION OF THE PROJECT " AURA " WE BUILT-
AURA is an interactive, luxury sensory-cognitive wellness workspace designed to reduce stress and foster deep flow states. Moving away from traditional, static software grids, AURA implements an HTML5 canvas vector flow field running at a locked 60 FPS. This interactive backdrop translates user mouse trajectories dynamically into fluid particle paths while feeding spatial data into a multi-voice synthesizer built directly on the native Web Audio API. The result is a living user interface where touch vectors create real-time, resonance-filtered ambient chords and evolving visual physics.
1. Link to project :- https://38425a77-aura-cognitive-flow-space.netlify.app/
2. Optional backup link to the editable Stitch workspace: https://stitch.withgoogle.com/projects/8647869648563302522
3. Brief explanation of how we used Stitch:
Google Stitch was the main control center for the whole project. We started by writing down all our styling rules—like our specific dark blue colors, see-through panels, and smooth 24-pixel corners—in a file named DESIGN.md (http://DESIGN.md). Because Stitch reads this file as a strict visual guide, its AI engine automatically placed all our volume sliders and screen controls perfectly without breaking our theme. For the advanced setup, we used a terminal tool called an MCP server to link our online design directly to our computer. This let our offline coding tools inside Google Antigravity 2.0 scan our project files, check our work, and make sure our music audio settings were perfectly synced.
4. Feedback -
The Good Parts: The DESIGN.md (http://DESIGN.md) file system is amazing. It completely stops the AI from changing your colors or fonts randomly on later edits, keeping the design looking clean and consistent. Also, the one-click Netlify export button makes publishing incredibly fast, letting you launch a live website in seconds without setting up complicated servers.
The Bottlenecks: Right now, if you manually tweak a design element directly on the canvas, those changes do not automatically update inside the text of your DESIGN.md (http://DESIGN.md) file.
My Suggestions:
Make it a two-way street: if we change a color visually on the screen, have Stitch rewrite that color token in the DESIGN.md (http://DESIGN.md) file automatically.
Add a "lock" button to elements on the canvas so that when the AI edits a specific box, it doesn't accidentally shift the positions of neighboring elements.
Build a simple visual menu for the local MCP server link so designers can connect their computer code without needing to type lines in a terminal.
5. A FULL WALKTHROUGH OF THE PROCESS : -
2
1
320
Context is King. 👑 I just stress-tested Gemini 3.1 Pro’s 2-million-token window against the EU AI Act.
Most RAG systems suffer from "Long-Range Dependency"—they forget what happened on page 5 by the time they hit page 200. I built a Technical Synthesis Engine that eliminates this blind spot.
What I did:
Engine: Google AI Studio (Gemini 3.1 Pro)
Logic: Temperature 0.0 for zero-hallucination accuracy.
Input: An almost 200 page technical manual.
The Result: A searchable policy assistant that cross-references sections with 100% citation accuracy. It found a "needle-in-a-haystack" regulatory penalty on page 142 that basic summaries missed.
0
240
How I compressed a 40-hour Real Estate Research cycle into a 12-minute AI Infrastructure.
Manual market research and asset creation are the biggest silent killers of brokerage margins. I’ve engineered a localized AI pipeline specifically for the Dubai/Abu Dhabi real estate markets that automates the "Research-to-Asset" lifecycle.
1) Live Data Ingestion: Utilizing Perplexity AI Pro to scrape real-time 2026 transactional data, rental yields (ROI), and infrastructure developments (e.g., Palm Jebel Ali Q2 absorption rates).
2) Contextual Synthesis: Deploying Gemini 3.1 Pro to process raw data into high-converting investor narratives and LinkedIn hooks.
3) Automated Creative Output: Direct mapping of synthesized data into Adobe Express Pro for branded, high-fidelity carousels and investor dossiers.
The Result: High-authority digital assets for top-producing agents delivered in minutes, not days. This system removes the "admin-bottleneck," allowing brokers to focus strictly on viewings and closing deals.
0
226
Can AI replace a $200k/year Investment Analyst? I built an Executive Intelligence Dashboard to find out.
As a part of my first solo project as an AI Productivity Specialist, I just open-sourced my AI Investment Research Framework on GitHub. It shows the exact Chain-of-Thought prompts I used with Gemini 3.1 Pro and Perplexity AI Pro to stress-test market data for a $15M VC scenario.
The Client requested to know specifically, if startups focusing on 'Autonomous Freight Auditing' have a real 'moat' or if they will be crushed by giants like SAP and Oracle in the next 18 months.
The Goal of my Project: Providing a data-backed "Investment Memo" that proves one can use AI to synthesize massive amounts of contradictory market data into a clear "Invest" or "Pass" recommendation.
Here is the finalised content done with Adobe Express.
0
208
Made and used a customised version of chatterbox multilingual with unlimited words to use the TTS model for AI based voice cloning. In this video recording I show the exact set of steps laying out how it is to be pulled off along with a sample at the end of the clip showing the output .
0
137