Building a New Generation of JavaScript ML with TensorFlow.js

Day 62 of 100 Days of AI — 🔗 Everything is Connected Today was one of those days where everything clicks into place. Every piece of the AI Newsletter is now talking to each other. Cloudflare Worker scrapes the sources on schedule → sends raw content to the Python backend → LangChain agents curate, synthesize, and rewrite → Jinja2 renders the final HTML email → Resend delivers it to subscribers. Next.js handles the frontend — clean landing page, subscribe form, all connected to the backend. OpenRouter powering the LLM calls. LangGraph orchestrating the agent pipeline. FastAPI holding everything together in the middle. Seven different services. One clean flow. Zero manual steps. The part that felt most satisfying — watching a raw scraped article go all the way through the pipeline and come out the other end as a polished newsletter section. Automatically. No human involved. That's what 62 days of building toward this feels like. Tomorrow — production deployment. Real subscribers. Live. Next: Production deployment — the newsletter goes live. #100DaysOfAI #BuildInPublic #LangChain #LangGraph #CloudflareWorkers #FastAPI #NextJS #AIEngineering #Newsletter #OpenRouter #Python

Decision tree regression remains a foundational machine learning technique, and in this hands-on piece, Dr. James McCaffrey walks through a full end-to-end JavaScript implementation built from scratch. The article shows how list-based storage and iterative tree construction can make decision tree regression more flexible, interpretable and easier to customize for future ensemble methods. See how decision tree regression works under the hood: https://lnkd.in/drqQ7GaN #MachineLearning #JavaScript #DataScience #AI #Programming

Day 53 of 100 Days of AI — 🔄 Revision Day Busy day. Didn't build much. But took the time to sit with everything — the newsletter architecture, the Cloudflare setup, the FastAPI backend, the agent pipeline plan. Making sure the full picture is clear before the agent work starts. Sometimes the most productive thing you can do is slow down and make sure you actually understand what you've already built. Agent work resumes tomorrow. Next: Building the synthesis agent — the brain of the newsletter. #100DaysOfAI #BuildInPublic #FastAPI #AIEngineering #Python #Newsletter #SideProject #LangChain

Most modern websites don’t just serve static HTML anymore, as they rely on JavaScript to render content dynamically. That means traditional scraping methods often fail… or miss critical data. So how do you actually scrape dynamic websites effectively? In our latest guide, we break it down: ✅ What “dynamic content” really means in practice; ✅ Why tools like BeautifulSoup alone aren’t enough; ✅ When to use headless browsers like Selenium or Playwright; ✅ How to build scalable scraping pipelines for real-world use cases. Read the full article on SapientPro's website. 🔗 Link in comments! #WebScraping #DataEngineering #Automation #Python #AI #Tech

🚀 Built Something Useful for Every Claude Developer While working with Claude Code, I realized one big gap — there’s no clear visibility into usage, tokens, or costs. So I built a solution 👇 🔗 https://lnkd.in/g7kCBnCn 💡 Claude Usage Dashboard A lightweight, local-first tool to track, analyze, and optimize your Claude usage in real-time. ✨ What it does: • Tracks token usage across sessions • Estimates API costs • Provides a clean dashboard + CLI insights • Detects anomalies & suggests optimizations • Includes a budget guard (yes, it can even stop overspending) ⚡ Best part: No setup headache. No dependencies. Just run it with Python. 🧠 Why I built this: When you're building with LLMs, visibility = control. This tool gives you exactly that. If you're working with Claude or exploring AI tools, this might help you 👇 Would love your feedback, ideas, or contributions 🙌 #AI #LLM #Claude #OpenSource #Developers #Python #BuildInPublic #GitHub

We benchmarked LLMs on their ability to analyze code files across 25 files in TypeScript, Python, Rust, Go, Markdown, and HTML on parameters like Search, Graph, Semantics, Integration, Security Mapping, Business Context, and JSON handling. Models can top leaderboards like SWE-Bench Pro while failing at basic creative and practical tasks. Optimizing for the test is not the same as optimizing for the work. Results: #claude-sonnet-4.6 ranked #1 with a weighted score of 121.2 at $1.66, the only Pareto Optimal pick among premium models. #claude-opus-4.6 scored 117.0 but at $8.00, sonnet-4.6 beats it cheaper. #glm-5v-turbo emerged as the best budget Pareto Optimal pick at just $0.28 with a score of 113.0. #gpt-5.4-nano is the most cost-efficient Pareto Optimal option at $0.04 with a score of 103.3. Notably, glm-5.1 despite ranking #1 on SWE-Bench Pro scored only 106.7 here at $0.60, beaten by cheaper alternatives. Models like Gemini 3.1 Pro Preview and GPT-4o-mini ranked near the bottom despite their popularity. The leaderboard confirms that benchmark performance rarely translates to real-world task quality. If you would like to reduce your AI agents cost including your AI copilots, please get in touch with us.

📣 Every LLM framework eventually adds async support. SynapseKit started there. There's a difference between async-retrofitted and async-native. Most frameworks started synchronous, bolted async on later, and shipped the seams - hidden event loop management, sync wrappers that infect the core, bugs that only surface under concurrent load. SynapseKit was designed async-first from the first commit. Every public API is async/await. No exceptions. No hidden sync layers underneath. If you understand Python and async, you understand SynapseKit. What that means in practice: → Stream tokens from any of 33 providers identically- not a special mode, the default → Run parallel graph nodes via real asyncio.gather - not simulated concurrency → No event loop surprises under load → Sync wrappers exist for scripts and notebooks - they call into the async layer, they don't replace it And the dependency story: 2 hard dependencies. numpy and rank-bm25. That's it. Everything else - LLM providers, vector stores, document loaders, tools - is behind an optional install extra. You pay only for what you use. No transitive conflicts. No 267-package installs. No surprise breakage when a framework you didn't know you depended on ships a breaking change. pip install synapsekit[openai] # 2 deps + openai pip install synapsekit[all] # everything Async-native. Minimal. Transparent. #Python #AsyncPython #LLM #RAG #OpenSource #AI #MLEngineering #SynapseKit

Just built my first RAG (Retrieval-Augmented Generation) Application! 🚀 The idea is simple upload any PDF and chat with it using AI. Ask questions, get answers all from your own document. 🛠️ Tech Stack: → FastAPI (Backend) → Mistral AI (LLM + Embeddings) → ChromaDB (Vector Store) → LangChain (RAG Pipeline) → HTML/CSS/JS (Frontend) ⚙️ How it works: 1. Upload your PDF 2. It gets split into chunks & converted to embeddings 3. Stored in ChromaDB vector store 4. You ask a question → relevant chunks are retrieved → Mistral AI generates the answer Built this from scratch while learning GenAI still building. 🔥 Agents & Deployment coming very soon! 🔗 GitHub: [https://lnkd.in/gNhZ2pJN] #GenAI #RAG #LangChain #FastAPI #MachineLearning #Python #BuildInPublic

Excited to share my latest project: a Dynamic Wumpus Logic Agent! 🚀🕵️♂️ I just wrapped up building a fully autonomous, Knowledge-Based web agent that navigates a randomized Wumpus World. But here is the catch: it doesn't use basic pathfinding or standard collision detection. It relies entirely on pure Propositional Logic to mathematically deduce safe paths! Built with a Python (Flask) backend and a reactive JavaScript UI, the agent senses its environment and proves its next move is safe before taking a single step. Building the AI from scratch was an incredible learning experience, especially tackling these two major hurdles: 🧠 1. The Logic Parser & CNF Translation The physical world is messy, but logic requires strict formatting. When the agent feels a 'Breeze', it's intuitive for a human to know a Pit is nearby. But teaching a parser to dynamically read the grid, translate a rule like Breeze <=> (Pit1 OR Pit2) into a clean, machine-readable Conjunctive Normal Form (CNF), and maintain that state in a growing Knowledge Base was a massive architectural puzzle. ⚙️ 2. The Resolution Refutation Engine To prove a cell is safe, the agent uses proof by contradiction. Writing the Resolution loop was tricky—standard theorem provers can easily get trapped in infinite loops or suffer from exponential memory bloat as clauses combine. By implementing a Set of Support strategy, I was able to optimize the algorithm to focus strictly on the target coordinates, allowing the backend to find contradictions and resolve safety checks in milliseconds. Check out the project in action! I would love to hear from other devs—have you ever tried building a custom inference engine or theorem prover? What optimization strategies did you use? Let me know below! 👇 #ArtificialIntelligence #Python #Flask #WebDevelopment #SoftwareEngineering #LogicProgramming #AI #TechProjects 🔗 Check out the Code repository here: https://lnkd.in/dgxRgFRw

🚀 Built & Deployed a FastAPI REST API Excited to share that I’ve been working on building high-performance REST APIs using FastAPI! 🔹 Designed scalable API endpoints 🔹 Implemented CRUD operations 🔹 Integrated request validation using Pydantic 🔹 Ensured high performance with async support 🔹 Tested endpoints using Postman FastAPI makes backend development faster, cleaner, and more efficient compared to traditional frameworks. Currently exploring deployment strategies and integrating APIs with AI/LLM-based applications 🤖 #FastAPI #RESTAPI #BackendDevelopment #Python #APIDevelopment #AI #MachineLearning