DEV Community: Hrishi Mehta

I Built an Entire Workflow Automation Platform Using the GitHub Copilot CLI 🤖✨

Hrishi Mehta — Sun, 15 Feb 2026 23:42:03 +0000

This is a submission for the GitHub Copilot CLI Challenge

What I Built

I built Sluice, a visual, node-based automation platform designed for developers who are tired of repetitive manual tasks.

We've all been there: "Can you summarize these PDF to text, md, etc ?" or "Can you change image type without losing quality of uploaded image ?" or "Just quickly verify this CSV data?" or "Suggestions to improve this code file?".

Instead of writing a new throwaway script every time, Sluice lets you drag and drop nodes to create reusable workflows.

Video Executing one flow - https://res.cloudinary.com/dfzqhhywm/video/upload/v1700000000/1f96fdaa-3673-4021-bbb5-35fb5d429b55_rknz56.mp4

Key Features:

🧠 AI Nodes: "Explain Content", "Analyze Code", and "Describe Scene". I integrated LLMs to not just process files but understand them.
📄 PDF Power: Watermark, Encrypt, Highlight Signatures, and Compress PDFs visually.
🔊 Audio Analysis: Detect emotion in audio files (because why not?).
💻 Developer Tools: A "Code Refactor" node that cleans up messy code and a "JSON Repair" node that fixes broken data structures.

It uses a Next.js frontend with React Flow for the canvas, and a robust FastAPI (Python) backend to handle heavy file processing.

My Experience with GitHub Copilot CLI

Wait, did I actually write code?

Okay, here's the kicker: I built this entire full-stack application using GitHub Copilot in the CLI.

I used the CLI agent for everything. You literally just prompt it, and it writes the code for you. It's not just "autocomplete" anymore; it's a full-on coding partner.

Why it's a Must-Try:

Prompt & It Codes: I didn't have to manually wire up the complex React Flow nodes or write the API endpoints. I just told the CLI: "Create a Properties Panel that dynamically updates based on the selected node string" and it scaffolded the entire component, imports and all.
MCP Servers are Insane: The Model Context Protocol (MCP) server integration is the real game-changer. It allows the CLI to interact with my local file system, run terminal commands, and even search the web contextually. It feels like the AI has "hands" inside my project.
Easy Model Switching: One minute I'm using a fast model for quick CSS fixes, and the next I'm switching to a reasoning-heavy model to debug a race condition in the backend. The ability to fluidly switch models within the same CLI session meant I always had the right brain for the job.
Complex Logic? No Problem:
- I had a messy engine.py file handling 20 different file operations.
- I asked the CLI to refactor the if/elif blocks for AI processing (explain, analyze, suggest).
- It rewrote the entire conditional structure to use a clean, dynamic prompting system, handling file type detection and fallbacks for binary files automatically.

Building this project felt less like coding and more like directing a highly skilled engineer. If you haven't tried the new CLI agent workflow yet, you're working too hard. 🚀

AI-Powered Recipe Discovery with Intelligent Search

Hrishi Mehta — Mon, 09 Feb 2026 07:38:06 +0000

Too much of tech, tired huh, lets do fun with bud Algolia :)

🍳 Auto-Yum: AI-Powered Recipe Discovery with Intelligent Search

Turn pantry chaos into gourmet meals — instantly.

Link - https://nutra-blond.vercel.app/

Auto-Yum is an AI-powered recipe platform that generates personalized meals based on the ingredients you already have, your dietary needs, and the time you can spare. Every recipe the AI creates becomes searchable for the entire community through lightning-fast intelligent search.

This isn’t just recipe generation.
It’s AI creation + smart discovery infrastructure working together.

🚩 The Problem

Home cooks struggle with three everyday challenges:

😵 Decision Fatigue

“What can I make with these random ingredients?”

🧩 Discovery Gap

Existing recipe sites rarely match your exact ingredients, diet, and time limit.

🔍 Search Limitations

Traditional search can’t understand:

Ingredient substitutions

Dietary nuances

Fuzzy matches like “pasta” → spaghetti or penne

💡 Our Solution: AI Generation + Intelligent Indexing

Auto-Yum combines AI creativity with powerful search infrastructure so every generated recipe becomes part of a growing, searchable ecosystem.

Algolia Capabilites

Auto Sync - Synchronize all recipes from MongoDB to Algolia search index

Link - https://nutra-blond.vercel.app/admin/sync

🤖 How the AI Works

Technology: Google Gemini 2.5-flash via Genkit

Generation Flow

User inputs:

Available ingredients

Dietary preferences

Time constraints

AI produces a complete, structured, nutritionally analyzed recipe.

🧠 AI Capabilities

✔ Ingredient Intelligence – Suggests substitutions and flavor pairings
✔ Nutritional Precision – Calculates macros per serving
✔ Food Safety Awareness – Cooking warnings & storage tips
✔ Professional Quality – Equipment lists and pro techniques
✔ Flavor Profiling – Describes taste and texture experience

Example Input:
"chicken, spinach, garlic, rice" + high-protein + 30 minutes

AI Output:
A full recipe with:

15 structured steps

35g protein per serving

Equipment list

Variations

Storage instructions

🔍 How We Use Algolia (The Brain of Discovery)

Algolia powers instant, intelligent discovery across all AI-generated recipes.

1️⃣ Automatic Indexing Pipeline

Every recipe is indexed with rich searchable attributes:

title, description

mainIngredients

ingredients.item (nested search)

searchKeywords (from original user input)

category, difficulty, source

2️⃣ Faceted Navigation

Users can filter recipes by:

🥗 Dietary Tags (Vegan, Keto, Gluten-Free, High-Protein)

🧑‍🍳 Difficulty (Easy / Medium / Hard)

⏱ Time Range (Quick meals vs slow-cooked)

🔥 Nutritional Goals (Calorie-conscious)

Each filter shows live result counts.

3️⃣ Smart Ranking

Popular and highly viewed recipes rise to the top using:

customRanking: ['desc(views)']

This creates a community feedback loop where the best AI recipes get discovered more often.

4️⃣ InstantSearch Experience

Using react-instantsearch, users get:

🔎 Real-time search results

🎯 Multi-select filters

📊 Live stats ("Showing 12 of 47 recipes")

🖼 Beautiful recipe cards

⚡ Sub-50ms search response time

5️⃣ Smart Searchable Attributes

Searching for “pasta” can return recipes containing:

Spaghetti

Penne

Fusilli

…even if “pasta” isn’t in the title.

That’s ingredient-level intelligence, not keyword matching.

🏗 Technical Architecture
Layer Technology
Frontend Next.js 15, React 19, TypeScript, Tailwind CSS
AI Engine Google Gemini 2.5-flash via Genkit
Search Algolia InstantSearch
Database MongoDB (source of truth)
Images Pexels API (auto-fetch per recipe keywords)
Sync Strategy

⚙️ Config Sync: Index settings applied on every batch sync

🌟 What Makes Auto-Yum Original
🤝 Dual Intelligence System

AI generates recipes → Algolia organizes and makes them discoverable.

Most recipe apps are static databases.
Auto-Yum is an ever-growing AI-powered food ecosystem.

🎯 Constraint-Based Discovery

“I have only vegetables and 20 minutes.”

→ AI creates the recipe
→ It gets indexed
→ Others can find it using filters later

📈 Community Learning Loop

Great AI recipes get more views → Ranked higher → Discovered more often.

The system learns from user engagement, not just data.

🚀 Proactive (Non-Chatbot) Intelligence

No chat conversation needed.

Input constraints → Get solution → Discover similar recipes instantly.

🎨 Usability Highlights

✅ 3-Step Flow: Enter ingredients → AI generates → Recipe instantly searchable
✅ <50ms Search: Instant results with live filters
✅ Mobile-First Design
✅ Accessible (keyboard + screen reader friendly)
✅ Real-time visual feedback for filters and results

🌍 Impact

For Users:
Never waste ingredients again. Always have dinner ideas.

For the Community:
Every generated recipe improves discovery for everyone.

For Health:
Accurate nutritional data supports dietary goals.

For Search Innovation:
Demonstrates search as infrastructure for AI-generated content.

🎬 Demo Flow

Visit /discover

Enter: "tomatoes, basil, pasta"

AI generates Classic Margherita Pasta

Recipe is auto-indexed

Go to /search

Search "pasta" → Find it instantly

Apply filters: Easy + Under 30 min → Results refine in milliseconds

🧠 Why This Is a “Non-Conversational AI Experience”

❌ Not a chatbot
✅ Proactive assistance
✅ AI generation embedded in workflow
✅ Intelligent retrieval via filters & search
✅ Every AI output becomes searchable knowledge

Algolia acts as the memory layer for AI creativity.

Welcome to the Gravity - By Antigravity, Space and Beyond :)

Hrishi Mehta — Sun, 01 Feb 2026 11:42:14 +0000

🚀 Space-Themed Developer Portfolio — Mission Control

An immersive, interactive developer portfolio designed as a futuristic mission control system. Built with React + TypeScript and deployed on Google Cloud Run, this portfolio transforms technical storytelling into a playable digital experience.

Instead of scrolling through a résumé, visitors explore projects, run terminal commands, and even unlock certifications through a hidden space game.

Link - https://new-portfolio-807524481289.us-central1.run.app

🌌 About Me

I’m Hrishi Mehta, a 2025 Computer Science graduate passionate about building at the intersection of:

🤖 AI/ML Engineering
💻 Full Stack Development
☁️ Cloud & DevOps

I believe portfolios should do more than list projects — they should demonstrate creativity, engineering depth, and problem-solving through interaction.

This project reflects how I think: immersive, technical, and experience-driven.

🎮 Interactive Portfolio Experience

This portfolio functions like a digital spaceship cockpit where recruiters can explore my work.

🕹 Space Game (Easter Egg)

A custom HTML5 Canvas space shooter where players dodge asteroids and unlock hidden certification messages. Gamified credential discovery turns passive viewing into an engaging experience.

💻 Interactive Terminal

A fully functional in-browser CLI:

Includes real command parsing, filtering, command history, and hidden easter egg commands.

🤖 Tactical AI Dock

A simulated AI analysis system that scans my profile and presents key strengths with animated “mission-ready” diagnostics.

🛠 Tech Stack — The Starship Arsenal

Frontend Command Center

React 18 + TypeScript
Vite
Framer Motion
Canvas API
Tailwind CSS
Lucide Icons

Cloud & Infrastructure

Docker (multi-stage optimized build)
Google Cloud Run (serverless deployment)
Nginx (SPA routing, caching, gzip compression)
Cloudinary CDN
Production security headers

AI Integration

AI-enhanced project descriptions
Simulated intelligent UI analysis systems
Gemini-inspired AI-themed interface elements

🌠 Design System — Mission Control Aesthetic

The entire interface follows a space-cyberpunk design language:

Glassmorphism panels with blur and glow
Neon domain color system
- Cyan → Web
- Purple → AI
- Green → Security
Animated starfields and parallax depth
Military-style project IDs (SITREP_01/AI)
Real-time system status indicators (ACTIVE • LIVE • SECURED)

🌟 Key Highlights

🎮 Gamified Portfolio Exploration

Certifications and achievements are discovered by playing, not just reading.

💻 Real Functional Terminal

Not a visual mockup — a working command system with dynamic rendering.

⚡ Performance Engineering

95+ Lighthouse score
~180KB gzipped bundle
<2s load time
Optimized Docker image (~25MB)

☁️ Cloud-Native Deployment

Runs serverless on Google Cloud Run with auto-scaling and global delivery.

♿ Accessibility & Responsiveness

Keyboard navigation, ARIA labels, WCAG-compliant contrast, and responsive layouts across devices.

🚀 Projects Featured (Mission Reports)

17+ interactive projects across AI, Web, and Security domains, presented as classified mission reports with live status indicators.

These include:

AI-powered document analyzers
NLP chatbots
ML recommendation systems
Graph database applications
Security automation tools
Real-time dashboards
Interactive browser games

Each project is structured to highlight problem, technology, architecture, and outcome.

🧠 Certifications & Experience

Certified across AI, cloud, databases, and security domains, with hands-on experience in:

AI/ML internships (LLMs, NLP, RAG systems)
Cybersecurity and ethical hacking roles
Backend engineering with Python and Java
Freelance full-stack cloud deployments

🛰️ What Makes This Portfolio Different

Most portfolios are static.

This one is:

🎮 Interactive

🤖 AI-themed

🚀 Immersive

☁️ Cloud-native

⚡ Performance-optimized

🎨 Visually engineered

It demonstrates not only what I know — but how I build, design systems, and think as an engineer.

📬 Contact

Hrishi Mehta

📧 mehtahrishi45@gmail.com

💼 LinkedIn: https://linkedin.com/in/hrishi-mehta-889732256

🐙 GitHub: https://github.com/mehtahrishi

“It’s not just a portfolio — it’s a mission simulation.”

👽 Alien Interview Simulator — Ace Your Next Intergalactic Tech Interview!

Hrishi Mehta — Fri, 09 May 2025 08:15:22 +0000

✨ Hey Fellow Devs!

I’m thrilled to unveil my submission for the Amazon Q Developer "Quack The Code" Challenge, under the Exploring the Possibilities category. 🚀

Say hello to the Alien Interview Simulator, a retro-styled, sci-fi themed web app that lets you test your tech chops by facing off against alien interviewers. Whether you're into Full Stack, Cybersecurity, or Cloud wizardry — there's a domain here with your name on it! 🚀🔮

🧠 What It Does

The Alien Interview Simulator lets users:

Choose from 6 technical domains
Complete a 2-round interview:
- Round 1: 5 Q&A questions
- Round 2: 2 coding challenges
Get instant feedback and a final score
Review past interviews in a detailed history section

Domains Available:

🖥️ Full Stack
📱 App Development
☁️ Cloud & DevOps
🧪 Software Testing
🔐 Cybersecurity
🕵️‍♂️ Ethical Hacking

🌌 Tech Meets Retro Sci-Fi

I leaned hard into the retro vibe with:

Animated space scenes: twinkling stars, orbiting planets, UFOs
CRT-style screen effects: scanlines, glows, and vintage UI containers
ASCII Art Titles: like the good old terminal days
Fully responsive for mobile and desktop

🛠️ Under The Hood

Frontend:

HTML / CSS / JavaScript
CSS animations for space vibes
JS-driven question handling and evaluation

Backend:

Flask (Python)
JSON-based question data
Flask APIs for Q&A delivery and scoring

Hosted on:

Render

🤖 Amazon Q Developer FTW

Amazon Q Developer was my go-to teammate for:

Generating Q&A + coding questions for each domain
Creating Flask routes and API logic templates
Speeding up JS logic with fast suggestions
Refactoring tricky logic through the CLI assistant

Seriously, Q made everything smoother and saved me tons of dev time.

🧪 Try It Out

🌐 App Link:
[https://alien-interview-simulator.onrender.com/]

Note: Please wait for 3 - 4 minutes as render takes time for respond

No login required — just pick a domain and dive into the cosmic quiz!

📸 Screenshots

🧠 Coming Soon...

Planned features:

AI-powered answer evaluation with Amazon Q or OpenAI
Personalized performance feedback
Multiplayer challenge mode
Custom question banks by user profile

🏁 Final Transmission

This build was such a fun mix of tech, design, and creativity. I loved blending nostalgic UI with modern dev tools like Amazon Q.

Massive thanks to the Amazon Q Developer team and DEV for sparking this fun coding challenge.

👌 Built with coffee, curiosity, and cosmic vibes.

Feel free to drop feedback, or reach out if you'd like help customizing your own alien interview setup! 🚀

📬 Get in Touch
If you enjoyed the project or have any feedback, ideas, or cosmic questions — I’d love to connect!
Feel free to reach out to me on Linkedin and let's geek out over code, aliens, or both. 👽💻