Blog

Every few months, something gets released that looks like infrastructure plumbing but turns out to matter more than the flashy launches. Model Context Protocol (MCP) is one of those things. If you’re a developer working with LLMs, MCP will change how you integrate AI into your workflows. Here’s an early-adopter perspective on what it is, why it matters, and how to actually use it. What Problem Does MCP Solve? Today’s AI tools are context-starved. You paste code into ChatGPT, upload files to Claude, manually copy database schemas into prompts. Every session starts from scratch. Every context window is a blank slate. ...

Extended thinking isn’t just “model thinks longer”—it’s a fundamentally different interaction model. If you’re prompting extended thinking models (Claude Opus, o1) the same way you prompt standard models, you’re leaving most of the value on the table. This post is a developer’s mental model for working with these systems: when to use them, how to prompt them, and what trade-offs to expect. How Extended Thinking Actually Works Standard LLMs generate tokens one at a time, each token conditioned on everything before it. The model “thinks” only as fast as it speaks. Ask it to solve a complex problem, and it often commits to an approach in the first few tokens, then rationalizes that approach even if it’s wrong. ...

The graveyard of failed AI features is full of chatbots nobody asked for. Every product team I talk to has the same story: leadership watched a GPT demo, got excited, and mandated “we need AI in the product.” Three months later, there’s a chatbot in the corner of the app that 3% of users have tried and 0.5% use regularly. As CPO at Entropy Labs, I’ve been on both sides of this. I’ve built AI features that users loved and killed features that seemed brilliant in demos but died in production. Here’s what I’ve learned about the difference. ...

Every LangChain tutorial ends right where the real work begins. You see a neat 50-line script that queries a PDF, and you think, “Cool, I’ll ship this by Friday.” Three weeks later, you’re debugging memory leaks, wondering why your chain silently returns empty strings, and questioning every decision that led you here. I’ve shipped LangChain-based features to production at multiple companies. Here’s what I wish someone had told me before I started. ...

I’ve been skeptical of every “game-changing AI release” for the past two years. Every few months, a new model drops and Twitter explodes with claims that AGI is here. Spoiler: it never is. But when Anthropic released Opus 4.5, something actually shifted in how I work. Not because it’s AGI—it’s decidedly not—but because it’s the first model that consistently delivers on complex, multi-step reasoning without falling apart halfway through. ...

Introduction If you've ever found yourself digging through product manuals, company wikis, or lengthy documents just to find a simple answer, you know the pain. The fact you're reading this suggests you're interested in how Generative AI can make that process less painful. Stick around for a few minutes, and I'll walk you through how we built a smarter FAQ bot using Google's Gemini API, Retrieval Augmented Generation (RAG), and structured output. This isn't just another chatbot; it's designed to give reliable, context-aware answers based only on provided information, minimizing the risk of making things up (hallucination). This example uses Google Car manuals, but the principles apply anywhere you have a set of documents you need to query effectively. I'm sharing my journey building this; it's a practical demonstration, not a definitive guide, so adapt the ideas to your needs! The Problem: Dumb Bots and Information Overload Traditional search methods or basic chatbots often fall short when dealing with specific document sets: ...

Introduction The fact that you have decided to read this behemoth of an article deserves admiration and tells me that you're serious about your academics and career (or are procrastinating on something else). Give me the next 20 mins of your life and I'll make you into a much more informed individual. Your Final Year Project (FYP) is one of the most important academic tasks in your degree. It can shape your future career, boost your portfolio, and improve your problem-solving skills. This guide will help you choose the right topic, advisor, tech stack, and strategy to ensure your FYP stands out. This guide is mainly targets FASTians because of my experience, but the advice can be applied to any university. Also, I claim to be no expert in this field. I'm just a student who's been through the process and wants to help others navigate it. So take my very opinionated advice with a grain of salt. Research & Development vs. Development When planning your FYP, it’s essential to decide which type of project best aligns with your interests, skills, and career goals. Generally, there are two broad categories: ...

Introduction As my POS system scaled, performance bottlenecks became increasingly apparent. Customers began complaining about slow bill generation times, which made checkout frustratingly sluggish. After profiling my Django APIs, I discovered that inefficient ORM queries were causing unnecessary database overhead, leading to significant slowdowns. This prompted a deep dive into ORM optimizations to reduce query execution time and improve the overall user experience. In this post, I’ll share how I optimized my Django ORM queries using select_related, prefetch_related, bulk operations, and query profiling tools to enhance the efficiency of my refund API and bill generation process. ...

Introduction As a developer, having a portfolio website is crucial for showcasing skills, projects, and expertise. I wanted a fast, minimal, and easily maintainable site, so I chose Hugo with the PaperMod theme. Best of all, I leveraged free tools for deployment, analytics, and discussions. Here’s how I built my portfolio website, hosted on GitHub Pages with a Porkbun domain. Hugo and PaperMod for a Minimalistic Look Hugo is a blazing-fast static site generator, perfect for a developer portfolio. I picked the PaperMod theme because of its: ...

Introduction When dealing with financial transactions in Django applications, maintaining an accurate ledger is critical. However, inefficient signal handling can lead to performance bottlenecks. In this article, we’ll explore an optimized approach to recalculating ledger balances while ensuring minimal database impact. The Problem A typical ledger system requires recalculating balances when transactions are inserted, updated, or deleted. Using Django signals, many implementations trigger redundant recalculations, causing excessive database queries and slowing down the application. ...