<feed xmlns="http://www.w3.org/2005/Atom"> <id>/</id><title>Chirpy</title><subtitle>A minimal, responsive and feature-rich Jekyll theme for technical writing.</subtitle> <updated>2026-08-05T05:17:29+00:00</updated> <author> <name>your_full_name</name> <uri>/</uri> </author><link rel="self" type="application/atom+xml" href="/feed.xml"/><link rel="alternate" type="text/html" hreflang="en" href="/"/> <generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator> <rights> © 2026 your_full_name </rights> <icon>/assets/img/favicons/favicon.ico</icon> <logo>/assets/img/favicons/favicon-96x96.png</logo> <entry><title>Breaking Big Problems into Small, Reliable Steps with Prompt Chaining</title><link href="/posts/breaking-big-problems-into-small-reliable-steps-with-prompt-chaining/" rel="alternate" type="text/html" title="Breaking Big Problems into Small, Reliable Steps with Prompt Chaining" /><published>2026-02-07T12:50:43+00:00</published> <updated>2026-08-05T05:12:51+00:00</updated> <id>/posts/breaking-big-problems-into-small-reliable-steps-with-prompt-chaining/</id> <content type="text/html" src="/posts/breaking-big-problems-into-small-reliable-steps-with-prompt-chaining/" /> <author> <name>your_full_name</name> </author> <summary>{% raw %} Large Language Models (LLMs) often feel intelligent enough to handle anything in a single instruction. But in real world applications, giving one massive prompt is like asking a human to cook, serve, clean, and manage accounts at the same time quality drops quickly. Prompt chaining treats an LLM like a team member in a workflow rather than a one shot oracle. By dividing a complex g...</summary> </entry> <entry><title>There is nothing Random inside a computer</title><link href="/posts/there-is-nothing-random-inside-a-computer/" rel="alternate" type="text/html" title="There is nothing Random inside a computer" /><published>2026-02-07T12:28:32+00:00</published> <updated>2026-08-05T05:12:51+00:00</updated> <id>/posts/there-is-nothing-random-inside-a-computer/</id> <content type="text/html" src="/posts/there-is-nothing-random-inside-a-computer/" /> <author> <name>your_full_name</name> </author> <summary>{% raw %} Have you ever wondered how your music app shuffles thousands of songs, or how a video game generates a brand new world every time you hit “New Game”? It feels like digital magic. We call it “random,” but in the world of silicon and circuits, true randomness is actually quite hard to find. In fact, your computer isn’t “guessing” at all. It’s following a recipe. The Secret Recipe: Th...</summary> </entry> <entry><title>Django Forms &amp;amp; Validations — From Simple to Advanced</title><link href="/posts/django-forms-amp-validations-from-simple-to-advanced/" rel="alternate" type="text/html" title="Django Forms &amp;amp;amp; Validations — From Simple to Advanced" /><published>2026-02-05T09:47:59+00:00</published> <updated>2026-08-05T05:12:51+00:00</updated> <id>/posts/django-forms-amp-validations-from-simple-to-advanced/</id> <content type="text/html" src="/posts/django-forms-amp-validations-from-simple-to-advanced/" /> <author> <name>your_full_name</name> </author> <summary>{% raw %} When I first started learning Django, forms looked magical. I would write a few lines, call is_valid(), and Django somehow knew whether my data was correct or not. Only later did I realize how much work Django does behind the scenes (batteries included) type conversion, sanitization, security checks, and structured validation. Forms are the front gate of your application. Every pie...</summary> </entry> <entry><title>MovieLens 360: User Retention, Recommendation &amp;amp; Engagement Analytics</title><link href="/posts/movielens-360-user-retention-recommendation-amp-engagement-analytics/" rel="alternate" type="text/html" title="MovieLens 360: User Retention, Recommendation &amp;amp;amp; Engagement Analytics" /><published>2026-02-05T09:19:17+00:00</published> <updated>2026-08-05T05:12:51+00:00</updated> <id>/posts/movielens-360-user-retention-recommendation-amp-engagement-analytics/</id> <content type="text/html" src="/posts/movielens-360-user-retention-recommendation-amp-engagement-analytics/" /> <author> <name>your_full_name</name> </author> <summary>{% raw %} Imagine You are working as a Data Scientist in “StreamFlix” – a Netflix-like platform Management Problems Users install app → watch few movies → disappearHomepage recommendations are weakContent team doesn’t know:Which genres retain usersWhat time people watchMarketing wants:Who to target with offers DATA SOURCE MovieLens Dataset (Core) https://grouplens.org/datasets/movielens/25m/...</summary> </entry> <entry><title>E-Commerce Customer 360, Churn &amp;amp; Revenue Analytics</title><link href="/posts/e-commerce-customer-360-churn-amp-revenue-analytics/" rel="alternate" type="text/html" title="E-Commerce Customer 360, Churn &amp;amp;amp; Revenue Analytics" /><published>2026-02-05T09:07:30+00:00</published> <updated>2026-08-05T05:12:51+00:00</updated> <id>/posts/e-commerce-customer-360-churn-amp-revenue-analytics/</id> <content type="text/html" src="/posts/e-commerce-customer-360-churn-amp-revenue-analytics/" /> <author> <name>your_full_name</name> </author> <summary>{% raw %} 1. Business Problem (Industry Scenario) You are hired as a Data Scientist for an online marketplace similar to Amazon/Flipkart. The company has 3 major issues Customers are silently churningMarketing budget is wasted on wrong usersRevenue forecasting is inaccurate Management Questions Who are our most valuable customers?Which customers will churn next month?What will be next 30 days...</summary> </entry> </feed>
