UI/UX Designer • No-code Builder • AI Architect
UI/UX Designer • No-code Builder • AI Architect
I built something wild for the Paper Challenge🚀
It turns any GitHub repo into a visual case study — instantly.
No writing. No designing.
Just drop a repo link… and the canvas builds itself.
That’s CodeSage💯
Most devs have solid projects…
but they’re buried in README files nobody reads.
CodeSage changes that.
It reads your actual code — architecture, stack, commits —
and transforms it into a clean, dark, presentation-ready case study.
The real unlock?
Paper MCP.
I connected my AI agent directly to the canvas.
So instead of designing manually…
the agent builds everything:
• Sections
• Layout
• Insights
• Structure
All generated directly on the canvas.
No drag. No drop.
Just output.
Pick any repo → get 3 analysis modes:
*Each one gives
→ Complexity score
→ PR velocity
→ Language breakdown
→ Full Refactor Roadmap
Try CodeSage: https://codesage-871524277866.us-central1.run.app/
Tech stack:
Paper MCP · Gemini API · GitHub API · Antigravity
22
58
1.3K
Finding freelance clients shouldn't take hours.
Prospectra is a Notion agent that hunts leads for you, scores them by priority, and writes your cold emails — automatically.
→ Finds real leads from across the web
→ Tells you who to reach out to first
→ Writes personalised cold emails instantly
→ Keeps your entire pipeline inside Notion Stop scrolling LinkedIn for hours.
Try it → https://www.notion.so/agent/3357b509492d801682d200929fc20ce0
Let AI fill your pipeline.
1
7
370
AI Trading Co-Pilot reimagines how humans interact with financial data.
Instead of overwhelming dashboards, the interface introduces an AI presence that observes, analyzes, and responds in real time. When a user selects a cryptocurrency, the AI activates — scanning price movement and liquidity signals through a cinematic analysis sequence before delivering a clear risk level and strategic suggestion.
https://ai-trading-co-pilot.figma.site/
The core innovation lies in the interaction:
A responsive AI panel that feels alive
Smooth state transitions from observation to insight
Subtle ambient motion that creates a futuristic, intelligent atmosphere
Built entirely in Figma Make, this prototype explores a new design language for collaborative decision-making — where AI acts as a co-pilot, not an autopilot.
5
374
Nocturnes of 2126✨
What if Van Gogh and Whistler had painted the night of 2126? 🌙 Nine nocturnes of a future city (robot hounds, rainy delivery bots, air ferries, a tree wired with light), painted with a custom Recraft style built from public-domain paintings at The Met and the Smithsonian.
I went digging through the open-access collections of The Met and the Smithsonian looking for the night. I found Vincent van Gogh’s 1889 Saint-Rémy paintings (Cypresses, Wheat Field with Cypresses, Olive Trees, Irises) for their swirling impasto, and James McNeill Whistler’s Nocturnes (Bognor, Valparaiso) for their deep blue darkness lit by small points of gold. I blended the two into a Recraft style, then chained a second style from its results to lock in a cobalt-and-amber night palette. Nocturnes of 2126 uses that 1889 brush to paint a future neither artist could imagine: robot hounds, delivery bots in the rain, silent air ferries, AR lenses and glass houses with solar roofs, all at blue hour.
The style is public, so try it yourself 👇
24
30
2K
UX & Service Designer crafting human-centered systems
I design. I build. I ship.
Figma → Framer → production. No handoffs or back and forth. Just a finished product.
Roy Studio has 2 spots this month.
If you know, you know. If you don't—royflows.com (https://—royflows.com)
0
208
Mainframe is a conceptual AI studio — brand system + full multi-page website, built entirely in Stitch. Landing page with animated states, five inner pages (Labs, Studio, Services, Openings), and a complete DESIGN.md (http://DESIGN.md) covering color, type, and layout. Monochromatic, editorial, cinematic. The kind of system that usually takes weeks — done in one session.
Started with brand tokens, used them as the foundation for every page. Iterated hover states and animations without leaving the design context. The generated DESIGN.md (http://DESIGN.md) became the actual handoff doc.
Fastest I've gone from concept to a coherent multi-page system. Want: auto-propagating token updates across pages, finer motion controls, native multi-page navigation. Otherwise — best design-gen tool I've used since Figma got auto-layout.
7
9
512
Just wrapped a custom store build and I'm genuinely proud of this one.
Minimal. Clean. The kind of ecommerce experience that doesn't shout—it just works. Product pages that breathe. A checkout flow so smooth it almost feels intentional. Collections that actually make sense when you're browsing.
The hero hits different when you scroll through it live. Real product imagery. Real storytelling. The whole vibe just clicks.
This is what I build for brands that know design matters. No template defaults. No generic flows. Just a store that converts because it feels right.
Demo's ready to show—thinking this could be something special for the right founder.
→ DM if you're building something like this.
1
115
I set a quick design challenge for myself: What would a high-end landing page look like for a national defense contractor or a private drone dealer? 🚁🔥
Check out my latest UI/UX concept: a cinematic, dark-mode experience for a next-gen tactical drone called "The Executioner." The goal was to blend intense military aesthetics with a sleek, minimalist tech UI.
Let's hear your thoughts in comments!
2
138
AI Automation Developer | n8n, Make & GoHighLevel
I build production AI agents that automate real workflows
I build production AI agents that automate real workflows
Built an LLM-powered question-answering application that lets users ask natural-language questions over large document corpora and get accurate, grounded answers, instead of manually searching through documents for the right section.
Designed and built the full RAG pipeline independently, from document ingestion through to answer generation, as a technical demonstration of production-grade retrieval-augmented generation using AWS-native tooling.
Key Challenges:
Documents exceeding token limits: Large source documents couldn't be fed directly into the LLM's context window, so they had to be broken down without losing meaning or context across chunks.
Finding the right context: With a large corpus, the system needed to reliably surface the specific chunks relevant to a given question, not just the most textually similar ones.
Grounded, accurate answers: Answers had to be based on the actual retrieved content, not the model's general knowledge, to avoid confidently wrong responses.
Working within a managed AWS ecosystem: Embeddings, storage, and generation all needed to work together cleanly using Bedrock-native models rather than a patchwork of external services.
Approach:
Document loading and chunking
Processed large documents into manageable chunks sized to stay within model token limits while preserving enough context for coherent retrieval.
Vector embeddings with Amazon Titan
Generated vector embeddings for each document chunk using Amazon Titan, capturing semantic meaning rather than just keyword overlap.
Vector storage and retrieval
Stored the embeddings in a vector database, enabling fast similarity search to pull the most relevant chunks for any given question.
RAG-based answer generation with Claude on Bedrock
When a question comes in, the system retrieves the relevant chunks and passes them as context to Anthropic Claude via Amazon Bedrock, which generates an answer grounded in the retrieved content rather than relying on parametric memory alone.
Results & Impact:
Accurate, source-grounded answers over document corpora too large to fit in a single context window.
A scalable retrieval architecture that separates document processing, embedding, and generation, so any of the three can be swapped or scaled independently.
A fully AWS-native RAG pipeline, demonstrating fluency with Bedrock's embedding and generation models working together in production patterns.
Tech Stack
Python · LangChain · AWS Bedrock · Amazon Titan · Anthropic Claude · FAISS DB
1
143
Built a virtual try-on application that lets users try on garments over WhatsApp. A user sends a photo through WhatsApp, and the app returns a realistic image of them wearing the selected garment, no app download or website visit required.
Designed and built the system end-to-end, from the WhatsApp messaging integration through to the try-on generation pipeline, as a self-contained product demonstrating conversational commerce for fashion/retail use cases.
Key Challenges:
- Frictionless UX over a messaging app: WhatsApp isn't built for structured app interactions, so the flow had to feel natural through simple image and text messages, not clunky commands.
- Reliable image handling: Incoming photos vary wildly in quality, lighting, and pose, and had to be received, processed, and matched with garment images reliably.
- Fast turnaround: Users expect a near-instant reply on a messaging app, so the backend had to handle image processing and model inference without long delays.
- Stitching third-party services together: Twilio's WhatsApp API and Gradio's try-on model weren't built to talk to each other, so the app had to bridge them cleanly.
Approach:
WhatsApp integration via Twilio
-Set up Twilio's WhatsApp API to receive incoming user images and send outgoing try-on results, handling the messaging layer end-to-end.
Flask backend as the orchestration layer
-Built a Flask application to receive Twilio webhooks, manage the request flow, and coordinate between incoming user images and the try-on model.
Virtual try-on generation with Gradio
- Integrated Gradio's virtual try-on model to generate the final garment-on-user image, returning a realistic composite result.
End-to-end flow design
- Connected the pieces so a user's WhatsApp message triggers the full pipeline automatically: receive image → process → generate try-on → send result back, all within a single conversation.
Results & Impact
- A working conversational shopping experience built entirely on a messaging app users already have open every day.
- Zero-download, zero-signup try-on flow — removes the biggest friction point in getting users to try a new AI-powered feature.
- A reusable integration pattern connecting Twilio, Flask, and a generative vision model, applicable to other WhatsApp-based commerce or personalization tools.
Provided Services & Solutions
📌 Conversational App Development
📌 WhatsApp API Integration (Twilio)
📌 Backend Development (Flask)
📌 Generative AI Integration (Gradio virtual try-on model)
📌 Third-Party API Orchestration
Tech Stack: Python · Flask · Twilio WhatsApp API · Gradio
If you want an AI-powered experience built directly into a channel your customers already use, like WhatsApp, let's talk.
1
70
Built and maintained a HIPAA compliant production medical AI scribe system that uses multi-step LLM agents to extract clinical entities directly from physician-patient conversations and turn them into structured medical notes, cutting down the manual transcription work clinicians used to do after every visit.
Multi-stage clinical workflow: Documentation, coding, and review each have different logic and conditional paths, and the system needed to branch correctly between them without losing context.
Clinical accuracy: Generated notes had to be grounded in real patient history and clinical guidelines, not just plausible-sounding text.
Production reliability: As a live system handling real conversations, every agent run needed to be observable, debuggable, and monitored for cost and latency in real time.
Non-technical requirements gathering: Clinical needs had to be captured accurately from stakeholders without a technical background and translated into precise agent logic.
Approach:
Stateful agent orchestration with LangGraph
Designed LangGraph-based agent workflows with conditional branching, allowing the system to move correctly across documentation, coding, and review stages based on conversation content.
Context-grounded note generation with RAG
Built a RAG pipeline on AWS Bedrock with embeddings, so every generated note is grounded in the patient's actual history and relevant clinical guidelines rather than generic output.
Full production observability
Integrated Langfuse across all agent runs to track token usage, latency, and model KPIs, giving the team visibility into system health and cost in production, not just at build time.
Clinical stakeholder collaboration
Ran requirements sessions directly with clinical staff, converting their documentation needs into concrete agent behavior specs and validation criteria.
Results & Impact:
~40% reduction in manual transcription time for clinicians using the system.
Clinically grounded output, with notes tied to real patient history and guidelines instead of unsupported generation.
Full production observability, with token usage, latency, and model performance tracked continuously.
A workflow clinicians could trust, built through direct collaboration rather than a black-box handoff.
Provided Services & Solutions:
📌 AI Agent Development (LangGraph)
📌 RAG Pipeline Development (AWS Bedrock)
📌 LLM Observability (Langfuse)
📌 Cloud Infrastructure (AWS Lambda, S3, DynamoDB)
📌 Stakeholder Requirements Translation
📌 Production ML Systems
Tech Stack
Python · LangChain · LangGraph · AWS (Bedrock, Lambda, S3, DynamoDB) · Langfuse · TypeScript · REST APIs
2
103
Overview 📖
Built an end-to-end agentic content creation pipeline for a fast-growing AI-powered SEO platform. The system chains multiple LLM agents together to research, draft, and optimize content automatically, replacing what used to be a manual, multi-step editorial process with a single automated workflow.
Collaboration 🤝
Partnered directly with the platform's engineering team to design and ship the automation layer that now sits at the core of their content operations, turning a bottlenecked manual process into a scalable, always-on pipeline.
Key Challenges 🤔
Multi-step content logic: Research, drafting, and optimization each require different context and tone, but had to feel like one coherent pipeline, not three disconnected tools.
Consistency at scale: Every piece of generated content had to match brand voice and pass compliance checks, without a human reviewing each one manually.
Orchestration complexity: Content jobs needed to trigger reliably from webhooks and third-party APIs, run through multiple agents in sequence, and fail gracefully without stalling the whole pipeline.
Performance under load: The backend had to stay fast and stable as content throughput scaled up.
Approach 🔍
Agentic content pipeline design
Designed a multi-step LangChain agent chain with tool-calling, where each agent (research, drafting, optimization) has a clearly scoped role and hands off structured output to the next.
Workflow orchestration with n8n
Built n8n automation workflows to handle webhook triggers, third-party API integrations, and job routing, removing the need for manual intervention at almost every stage.
Brand voice & compliance enforcement
Layered in structured prompting and validation steps so generated content stays on-brand and passes compliance checks automatically, at scale.
Backend performance tuning
Optimized FastAPI endpoints and managed Azure-hosted PostgreSQL databases to keep latency low under high content-throughput conditions.
Results & Impact ✨
~60% reduction in manual intervention across the content pipeline, freeing the team to focus on strategy instead of babysitting workflows.
Consistent brand voice at scale, with compliance checks running automatically instead of manually.
Reliable, low-latency infrastructure validated under real content-throughput loads.
A reusable agentic architecture the platform can extend to new content types without rebuilding the pipeline.
Provided Services & Solutions ✅
📌 AI Agent Development (LangChain)
📌 Workflow Automation (n8n)
📌 LLM Integration (GPT-4, Claude)
📌 API Development (FastAPI)
📌 Cloud Database Management (Azure, PostgreSQL)
📌 Architecture Design & Consulting
Tech Stack
Python · FastAPI · LangChain · n8n · GPT-4 · Claude · Azure · PostgreSQL
2
102
AI Agent Developer & Engineer | MCP, LLM apps, automation
- 1x
- Hired
- 5.0
- Rating
- 62
- Followers
AI Agent Developer & Engineer | MCP, LLM apps, automation
Design Head & Product Designer at Pencil & Screen
- 5.0
- Rating
- 35
- Followers
Design Head & Product Designer at Pencil & Screen
A website should do more than look good. It should communicate clearly.
A website concept for Anant Growth, bringing web design, content strategy, and visual communication together in a playful, approachable digital experience.
3
125
Payment Screen - Not every design decision needs to be loud.
Sometimes, a subtle shift in visual hierarchy is enough to guide people toward the right choice without forcing it.
For Analytical Investments, I designed the pricing experience so the journey from the $0 plan to the $5 premium plan felt intentional rather than persuasive. Through thoughtful UI, UX, visual cues, hierarchy, and product design principles, we helped users naturally recognize the added value of the premium offering, making the decision feel informed instead of influenced.
1
2
131
AI Engineer | Conversational AI, Agents & Backend Automation
What happens when your assistant turns into your creative partner?
This is what we built few months back, a Conversational AI Design Assistant that could generate designs using natural conversation. The goal was to bypass traditional prompt engineering and replace it with natural conversation
The experience was fulfilling, with learning failure and overcoming everyday challenges. Looking forward to share more such project
If anyone is working on exciting projects, and believe I can contribute in any capacity, let's have a chat
2
1
223
Competitor Price Monitor | n8n + Google Sheets
Keeping track of competitor prices becomes repetitive when a retailer manages several product categories and regularly adds new SKUs.
I built this automation around TechNest Accessories, a simulated electronics retailer, with a practical brief: monitor comparable competitor products while keeping the solution affordable and easy to manage.
The budget shaped the approach. Product discovery and matching stayed manual: the retailer enters its own SKU, selling price and chosen competitor URL in Google Sheets. This keeps control over which products are compared and reduces the complexity of the build.
Once a listing is selected, the repeated checking is automated.
The workflow reads active listings, retrieves competitor prices and availability, and compares each result with both the retailer’s price and the previously recorded competitor price. It then updates the Current Prices tab and appends a timestamped record to Price History.
The retailer can manage everything from the sheet—add listings, update selling prices, or pause monitoring with a Yes/No dropdown.
The workflow also handles failed page requests and price extraction. It records the error, preserves the last valid price and continues to the next listing. A successful later check clears the error.
I tested the build with two Portronics charger listings, confirming price comparisons, historical records and recovery after a deliberately failed check. The workflow supports scheduled daily checks and manual runs.
The result is a working prototype that brings selected competitor prices into one place, highlights meaningful differences and preserves a record for review—while leaving product selection and pricing decisions with the retailer.
Built with: n8n, JavaScript, HTTP requests and Google Sheets.
Independent portfolio project based on a simulated client brief. Images show recorded test data and simplified views of the working system.
1
137
How I Built My Own Telegram Lead Capture System in n8n.
The goal was simple: create a Telegram-based lead capture system that could collect enquiries in a structured way, remember where each user was in the conversation, validate the information, normalize budgets across different currencies, classify leads, and finally store everything cleanly in Google Sheets.
I come from a Python background, so writing the chatbot logic in code would have been the easier route for me. But for this project, I deliberately chose to build the conversational flow using native n8n nodes instead of relying on a Code node. I wanted to understand how state management, branching, routing, and multi-step conversations could be handled visually inside n8n.
I only used code later where it made more sense—validating lead data, parsing budget information, detecting currencies, converting values to USD, and classifying higher-value leads.
At the moment, this system does exactly what I need it to do. If the volume of leads grows in the future, I’d extend it further—for example, automatically sending myself an email notification whenever a high-ticket lead comes in.
For now, though, I wanted to keep it practical rather than over-engineer it.
Built with: Telegram, n8n, JavaScript, Google Sheets, n8n Data Tables, and a currency conversion API.
1
169
Where most Sales Manager go wrong isn't lack of data, it's getting overwhelmed with numbers and targets. What actually matters is not numbers, but "why" behind it.
So we built an Agentic AI Sales Engine that sits on your Telegram, dissects the "why" behind what's happening in your sales team. It doesn't just throws number but tells you why someone is falling short while another pulling ahead, surfaces the operational bottlenecks underneath the numbers, and suggests what can actually be done better, all in real time at 0 infrastructure cost.
Problem:
A Sales Manager needed a fast way to check teams performance, calls, leads, conversions, pipeline value, but without opening spreadsheets or chasing manual reports. But raw numbers alone don't tell you what to do. Two reps can have identical conversion rates for completely different reasons. The manager needed something that could reason about the data, not just report it but by answering questions like "who needs attention today?" or "why is Rahul underperforming?"
What We Built
A fully automated Telegram bot, powered entirely by a self-hosted n8n workflow, that reads live data from Google Sheets and combines two layers: hard KPI reporting on demand, and an AI reasoning layer that interprets those numbers into a story a manager can act on.
The "Why Layer"
This is a part that makes it more than a dashboard, instead of just telling Rahul 12% conversion, the engine reasons over calls, leads pipeline and conversion patterns together and drives an analysis thereby providing the right suggestive next steps.
Skills Demonstrated
:Workflow automation & API orchestration (n8n)
:OAuth 2.0 debugging and Google Cloud API setup
:Data processing / aggregation logic (JavaScript in Code nodes)
:LLM integration with grounded, hallucination-resistant prompting
:Conversational bot design (Telegram Bot API)
:Building production-usable tools on a strict zero-cost budget
1
215
Branding, Designing, Product & Web Design that convert.
I didn’t want to build another portfolio website.
Most portfolio websites follow the same formula: a hero section, a few projects, some text, and a contact button.
I wanted to experiment.
Since this was my own website, I gave myself the freedom to break the usual rules and explore what a future-facing website could feel like.
I combined 3D elements, motion, interactive experiences, bold visual transitions, and unexpected design details to create something that feels less like a portfolio and more like a digital experience.
The goal wasn't simply to make it look futuristic.
Every element was an opportunity to explore how design, technology, motion, and AI can come together to create a website that feels alive.
And I'm not treating it as finished.
This website is my playground — a place where I can continuously experiment with new AI capabilities, interactions, 3D experiences, and ideas that I wouldn't necessarily get to test on a traditional client project.
Because if I'm going to build the future of digital experiences for others, I want to experiment with it myself first.
0
46
Marketing beyond the algorithm: How I built a trust-led strategy for a real-estate brand.
They didn’t need more marketing. They needed the right marketing.
When this real-estate client was launching a new venture, their first requirement was simple: they wanted the brand to feel premium.
They approached me to create their logo and brochure, with a clear goal of building a visual identity that looked credible, sophisticated, and trustworthy.
But as we worked together, the conversation went beyond design.
They asked me to take over their marketing — but with one condition:
“Don’t market us like everyone else.”
So I started with the most important part: understanding the customer.
I studied their competitors both online and offline, looked at how similar real-estate businesses were attracting buyers, spoke to the realities of their market, and went deeper into who their customers actually were.
And I found something important.
Their audience wasn't necessarily spending their time consuming social-media marketing content. Many of their potential buyers came from smaller towns, where purchasing decisions were built around something much more powerful:
Trust. Reputation. Word of mouth. Personal relationships. And seeing the opportunity in real life.
So instead of forcing a typical “digital marketing” strategy onto the business, I built a trust-led, hyperlocal marketing approach around how their customers actually think and buy.
The strategy focused on combining:
Offline presence + local relationships + premium branding + targeted digital visibility + word-of-mouth
Because when you're selling real estate, you're not simply selling a property.
You're selling confidence in a decision worth lakhs or crores.
And that requires understanding the buyer before choosing the marketing channel.
0
56
From “I have no idea” to a brand that feels like her.
When my client was starting her business, she knew what she wanted to build — but had no idea what her brand should look or feel like.
What colours?
What style?
What kind of logo would people remember?
We started with a brand identity consultation, where I helped her turn her ideas into a clear visual direction from the personality of the brand to the colour palette and logo concept.
The goal was simple: clean, impactful, and memorable.
Today, her business is live with a brand identity she feels confident about, and a design she genuinely loves.
Sometimes, good branding isn’t about making something beautiful.
It’s about helping a business finally see itself.
0
80
