Prompt Engineering Projects in Bahadurgarh

Prompt Engineering Projects in BahadurgarhPrompt Engineering Projects in Bahadurgarh

Cover image for This project serves as a

This project serves as a proof-of-concept for "Timecraft," a luxury timepiece brand. My goal was to prove that AI can maintain the rigorous standards of high-end commercial filmmaking. By applying classical cinematography techniques to generative AI, I produced a broadcast-quality sequence that captures the weight, texture, and precision of a mechanical luxury product.

104

Recreating Airbnb website for MagicPath Hackathon

Cover image for 🐉 Dragon in the Drawer.
A

🐉 Dragon in the Drawer. A child drew a dragon. 💬 And said: “the dragon is mad because the people woke him up… so now he’s burning all the buildings and they’re running.” 🎬 I turned that into a film. ✨ Just a drawing, a sentence, and a name — and it becomes a full story: Character → Story → Animation → Film — ❤️ This project is close to my heart. I built it for a girl named Angel. She was very ill when she was born. Our whole family prayed for her. She survived — so we called her Angel, because that’s what she felt like to us. I haven’t seen her in a while… but I wanted to create something she could feel. — 🌱 Because every child deserves to see their imagination come alive. Not just as drawings… but as stories they can watch, feel, and remember ✨ — Try👇 https://studio.morphic.com/en/workflows/019dca9f-eb8f-7392-b81d-bffe4a8a388f/dragon-in-the-drawer

753

Reseach Paper presentation

mafia character

Cover image for Syntra — AI Productivity Engine

Most

Syntra — AI Productivity Engine Most productivity apps expect you to organize your life. Syntra does it for you ⚡ You start with a messy brain dump 🧠 Syntra converts it into structured tasks, a 7-day plan, and real-time insights — instantly. The interface itself was generated using Paper MCP 🧩 → turning abstract system logic into a fully designed, interactive UI in real time. → bridging idea → structure → interface seamlessly. Try: 🔗 https://syntra-493723.uc.r.appspot.com/ (https://syntra-493723.uc.r.appspot.com/)🔗 https://github.com/omshukla24/Syntra Built with: ⚙️ Next.js + TypeScript 🧠 Google Gemini 2.5 Flash 💾 localStorage (no backend / no DB) 🎨 CSS Modules (no Tailwind) 🎬 Framer Motion 🧩 Paper MCP Runs entirely locally 🔐 No setup. No manual planning. Just chaos → structure → execution 🚀

600

Cover image for Most designers don’t know why

Most designers don’t know why their work is bad. They just feel it. So I built AUTOPSY ⚡ Upload a design → It tells you what’s wrong Why it fails How to fix it Then shows the fix + the best version with a cinematic reveal 🎬 Same design. No guessing. Try it: https://app.flora.ai/techniques/autopsy #FLORATechnique

360

Cover image for We think products belong to

We think products belong to their time. They don’t. They’re just designed that way. So I built WARP ⚡ A system that removes time as a constraint and lets any object exist across eras. One product → Reimagined as an ancient artifact A Bauhaus object A 60s hallucination A cyberpunk machine A 2150 future form Then everything converges into a single cinematic film 🎬 Same object. Different timelines. Completely different meaning. This isn’t about style. It’s about how design adapts — And what happens when it’s pushed beyond its era. Try it: https://app.flora.ai/techniques/warp

447

Cover image for I kept noticing the same

I kept noticing the same thing: Different brands. Same visuals. Every category has invisible rules — and most brands follow them without realizing it. So I built DISRUPT ⚡ A system that takes a product and: • Identifies the clichés holding the category back 🔍 • Creates 3 distinct disruption strategies • Translates strategy into actual visuals 🎯 • Places them into real campaign contexts 🏙️ • And brings it all together into a short film 🎬 The goal wasn’t to generate better images. It was to make better creative decisions repeatable. That’s what DISRUPT does. Try it: https://app.flora.ai/techniques/disrupt Built for the FLORA x Contra challenge

382

Cover image for Freelancers lose thousands of dollars

Freelancers lose thousands of dollars every year to scope creep. You say "yes" to a quick favor, and suddenly you're doing hours of unpaid work. 💸 Enter NeuraFlow 🧠 — an autonomous CI/CD pipeline for your freelance contracts. No chatting with AI bots. No manually copying prompts. Just drop a client proposal or change request into your database, change the status to "Pending Signature," and NeuraFlow runs completely in the background to: 🔍 Audit Proposals: Flags dangerous, vague phrases and provides concrete, copy-paste rewrites to protect your boundaries. ⚖️ Guard Your Scope: Compares mid-project requests directly against your original signed SOW. 🛑 Push Back Professionally: Automatically verdicts requests as "Out of Scope" and drafts a diplomatic email with a calculated change order estimate ($). 🚩 Track "Repeat Offenders": Detects clients who constantly ask for free work across multiple projects. ⚡ Fire Real-Time Alerts: Sends instant Gmail & Slack notifications when a high-risk scope threat is detected. Why it's reusable (Build Once, Reuse Forever): NeuraFlow works for any freelancer, agency, or consultant in any industry. A vague scope is a universal threat. ✅ Zero setup per client: The text is the context. Just paste and protect. ✅ Database-driven autonomy: No chat interfaces. Just change a Notion status and walk away. Your profitability, guarded autonomously. 🚀 🔗 Try the Agent: https://www.notion.so/marketplace/custom-agents/neuraflow (https://www.notion.so/marketplace/custom-agents/neuraflow)📁 Duplicate the Database: https://www.notion.so/3338770f9c6d80b4bf6cd11df38527fd?v=3338770f9c6d80fba613000c8957e5f7&source=copy_link

209

Cover image for NanoMech: The Real-Time Multimodal AI

NanoMech: The Real-Time Multimodal AI Trading Assistant 📈🤖 Built for the Gemini Hackathon Traders know that in the market, seconds equal dollars. By the time you switch between your chart, your analysis tools, and your risk calculator, the candle has already moved, and your setup is gone. I wanted to fix this. For the Gemini Hackathon, I built NanoMech—an AI that sits on top of your screen, sees exactly what you see, and gives you a complete trade plan in seconds. No API keys required, and no leaving your chart. 💡 The Solution NanoMech runs as two frameless, transparent overlays on top of any trading platform. It uses Google Gemini 2.5 Flash's multimodal vision capabilities to visually read your screen and deliver instant insights. Overlay 1: Market Analysis Trend: Analyzes bullish/bearish market structure and moving average crossovers. Liquidity: Evaluates order book depth, bid/ask walls, and support/resistance zones. Momentum: Breaks down candlestick patterns, volume behavior, and price velocity. Overlay 2: Trade Setup & Risk Management AI-Extracted Targets: Instantly provides Entry Price, Target Price, and Stop Loss. Live CALC Engine: Calculates Risk Amount ($), Position Size (Units), and Risk-to-Reward (R:R) Ratio. Everything updates live as you type in your desired risk percentage. 🛠️ How It Works (Under the Hood) Vision-to-Text Processing: Captures the screen in real-time using the mss library and sends the raw screenshot to Google Gemini 2.5 Flash via the Google GenAI SDK. Prompt Engineering: Engineered strict structured prompts using [ANALYSIS] and [TRADE] tags to force the LLM to output reliably parseable price data. Regex Extraction: Uses regex to pull the exact Entry, Target, and Stop prices from the AI's response and wire them directly into the local risk calculator. Custom Desktop UI: Built always-on-top transparent overlays using Python's Tkinter, utilizing threading to keep the UI fully responsive during API calls. Hands-Free Scanning: Integrated a global hotkey (Ctrl+A+I) and an Auto Mode that scans the chart every 20 seconds. 🧗‍♂️ Challenges Overcome Structured LLM Outputs: Getting an LLM to consistently return prices in a parseable numeric format is notoriously tricky. We solved this with rigorous prompt engineering and robust fallback handling. Thread-Safe UI: Tkinter isn’t thread-safe. We engineered a solution to route all UI updates through root.after() callbacks from the active analysis thread. UX/UI Friction: Tuning the transparency and colors so the text remains readable across both dark and light chart themes, while ensuring our global hotkeys didn't conflict with native trading platforms. 🚀 What We Learned & What's Next This project proved just how incredibly capable Gemini 2.5 Flash is at visual reasoning. It accurately identified complex candlestick patterns, moving averages, and volume spikes from a raw image alone. The Roadmap for NanoMech: Voice Output: Speaking the trade setup aloud for a 100% hands-free experience. Multi-Monitor Support: Allowing users to select which screen the AI tracks. Cloud Hosting: Running NanoMech as a scalable web service on Google Cloud Run. Trade Logging: Automatically tracking how the AI's setups perform over time. 💻 Built With Python | Google Gemini 2.5 Flash | Google GenAI SDK | Google Cloud | Tkinter | mss | pillow | Regex Ready to try it out? Check out the code and run it yourself: https://github.com/omshukla24/NanoMech

112