Two claps → my entire workflow is ready 👏👏 I built a small automation using Python and Claude that listens for two consecutive snaps/claps and instantly sets up my working environment. Once triggered, it automatically: • Opens Claude • Launches Chrome with my main tabs (Outlook, tracking Claude usage, and Lovable for web development) The idea was simple: reduce the friction of getting started and make my workflow faster and smoother. Instead of manually opening everything every time, it’s now done in seconds with a single trigger. Projects like this are helping me explore how AI and automation can be integrated into everyday tasks to improve efficiency and productivity. Looking forward to building more systems like this. 🚀 #AI #Python #Automation #Productivity #DeepLearning

What if your portfolio could talk back? I built an AI agent that represents me on my website — answers questions about my background, captures leads, and logs anything it doesn't know. All powered by Gemini 2.5 Flash + tool calling. No framework. Pure Python. The two tools it uses: 🔧 𝐫𝐞𝐜𝐨𝐫𝐝_𝐮𝐬𝐞𝐫_𝐝𝐞𝐭𝐚𝐢𝐥𝐬 — captures name + email when someone's interested 🔧 𝐫𝐞𝐜𝐨𝐫𝐝_𝐮𝐧𝐤𝐧𝐨𝐰𝐧_𝐪𝐮𝐞𝐬𝐭𝐢𝐨𝐧𝐬 — logs gaps so I can improve it over time Every lead, every unknown question → instant push notification to my laptop/phone via ntfy.sh. The whole agentic loop is just ~50 lines of Python: • Build messages array • Call LLM • If tool_calls → execute → feed back • Repeat until done Frameworks abstract this. But writing it raw makes you actually understand what's happening under the hood. GitHub → https://lnkd.in/eB2VwqDs This is step 1 of building my Personal Concierge Agent in public. Step 2: rebuilding this as a full Next.js + FastAPI web app — proper UI, real deployment. Follow along if you're into agentic AI, Python, and building real things — not just demos. #AgenticAI #Python #BuildingInPublic #LLM #Gemini

Stop using Pandas for everything. I just published a full breakdown of 7 Python libraries that are redefining how developers build in 2026 with install commands + real code examples for each. Here's the quick cheat sheet: ⚡ Polars → 10x faster than Pandas for big data 📄 MarkItDown → Converts PDFs/Word docs into AI-ready Markdown 🤖 Smolagents → Build your first AI agent in 10 lines 🧑✈️ GPT Pilot → An AI that writes entire features, not just autocomplete 📱 Flet → Build web + mobile + desktop apps in pure Python 🛡️ Pyrefly → Catch bugs BEFORE you run your code (Meta-built) 🌐 Morphik-Core → AI that understands images and videos, not just text You don't need to learn all 7 today. Pick the one that solves YOUR problem right now. Working with data? → Polars Building an app? → Flet Curious about agents? → Smolagents The full blog (with code examples for every library) is linked in the comments 👇 Which of these are you already using? Drop it below 🔽 #Python #AI #MachineLearning #Programming #Developer #TechIn2026 #AITools #OpenSource #PythonDeveloper #CodingTips

SmartCart.AI Why overpay when your cart can think for you? An AI-assisted shopping companion that tracks prices and emails you instantly when your desired deal appears. Built end-to-end leveraging AI to move faster, think sharper, and build smarter. Stack: React • Vite • Framer Motion • Python • MongoDB This is just the first version—next step: deeper intelligence. #AIProjects #SmartCart #FullStack #TechBuilders #Innovation https://lnkd.in/geMKuhGv

Building with AI and hosting platforms is interesting because it shows just how important expertise is in various areas (design, UI, frontend, backend and so on) in order to bring something fully to life, but also how rewarding it can be to create functioning niche solutions for individual (or group) painpoints even if they aren’t built to scale or look pretty. Kind of like the new way of writing python scripts- if you are able to properly define the problem and the solution needed you can then work with the AI to arrive to a neat solve.

Python: The Brain Behind Your Favorite Apps Ever wonder how apps "know" exactly what you need? Python is the engine under the hood of the world’s smartest websites, using AI to create personalized experiences just for you. From recommending your next favorite movie to providing instant customer support, it’s the technology making the web feel more human. Discover how we’re building a smarter digital world at Artemee.com!

I built a House Price Prediction App that estimates property prices based on key features such as lot area, construction year, overall condition, basement size, and location-related attributes. 🔧 Tech Stack: Python, Pandas, NumPy Scikit-learn (model development) Streamlit (interactive web application) 💡 Key Learnings: Data preprocessing: handling missing values and encoding categorical variables Maintaining feature consistency between training and prediction Building an end-to-end ML workflow (data → model → UI) Debugging practical issues like feature mismatches and NaN values 🖥️ The app provides a simple interface where users can input property details and get an instant price prediction. This project helped me move beyond theory and understand how to turn an ML model into a working application. 🔗 GitHub: https://lnkd.in/gGtxMZRa #MachineLearning #DataScience #Python #AI #Streamlit #LearningByDoing

I’ve spent a lot of time in the Next.js, Python, and SQL Server ecosystem, building systems like my Plate Making System for flexography. But over the last few months, my workflow has undergone a massive shift thanks to AI. Using tools like coding assistants hasn't just made me faster; it’s changed how I solve problems. Instead of manual data entry scripts, I'm now building AI agents to handle the heavy lifting. My biggest takeaway? AI doesn't replace the need for strong foundational skills. You still need to know how to structure a database and manage a GitHub repo but AI allows you to spend more time on the architecture and less time on the syntax. #FullStack #NextJS #AIinEngineering #WorkflowOptimization #BuildInPublic

🚀 Introducing ALGO_TRACKER.AI – Bridging Machine Learning with Static Code Analysis for Python. As software systems scale, quantifying Technical Debt and maintainability becomes crucial. Traditional rules-based linters often miss the complex interplay of metrics that define genuine code risk. To address this, I built ALGO_TRACKER.AI, an intelligent auditor that moves beyond rigid rules. It leverages a trained XGBoost model to analyze static code metrics (LOC, Cyclomatic Complexity, Halstead Metrics) recursively fetched from any public Python repository via the GitHub API. The goal is simple: Provide developers and tech leads with a predictive, probability-based "Bullish" (Clean/Maintainable) or "Bearish" (High Technical Debt) rating for their codebase. Key Features: 🔹 Deep recursive scanning of Python (.py) files using GitHub’s /git/trees API. 🔹 Static Metric Extraction (Radon/Lizard) to quantify complexity. 🔹 Intelligent Risk Prediction using an optimized XGBoost classifier. Tech Stack (High Performance & Scalable): ⚛️ Frontend: React, Tailwind CSS (Deployed on Netlify) ⚡ Backend: FastAPI (Python), (Deployed on Railway) 🤖 Machine Learning: Scikit-learn & XGBoost Check out the working prototype here: https://lnkd.in/g2tVERcH #MachineLearning #SoftwareEngineering #Python #FastAPI #ReactJS #FullStack #ArtificialIntelligence #Innovation

🏡 House Price Prediction App! I developed a Machine Learning-based web app using Python & Streamlit that estimates house prices based on important factors such as: ✔️ Area (in square feet) ✔️ Number of bedrooms ✔️ Property age ✔️ Distance from the city center ✨ Highlights of the project: Interactive and clean UI built with Streamlit Easy-to-use input fields for users Integrated ML model for accurate predictions Instant results display 🎯 What I learned while building this: Data cleaning & preprocessing techniques Working with regression algorithms Deploying ML models into web apps Designing simple and effective user interfaces 🛠️ Tech Stack: Python | Pandas | NumPy | Scikit-learn | Streamlit 🔗 Check out the project here: https://lnkd.in/ghhUHEGM 💡 Next improvements I’m working on: 🔹 Enhancing model performance 🔹 Adding visual analytics & charts 🔹 Improving UI with advanced features #MachineLearning #Python #AI #DataScience #Streamlit #Projects #BuildInPublic #Learning