HARIPRIYA

Why FastAPI Auto-Generates API Docs (And How to Customize Them)

Posted on Mon 27 September 2027 in Tutorial • Tagged with FastAPI, Python, API-docs, Swagger, OpenAPI

Why This Matters

If you've built even a basic FastAPI app, you've probably stumbled onto /docs and been pleasantly surprised — a fully interactive API documentation page, complete with every endpoint, request schema, and a "Try it out" button, without writing a single line of documentation yourself. This isn't a small …

Streaming AI Responses in FastAPI Using Server-Sent Events (SSE)

Posted on Sat 26 September 2026 in Tutorial • Tagged with FastAPI, Python, SSE, streaming, GenAI, LLM

Why This Matters

If you've used ChatGPT or Claude, you've seen the response appear word by word instead of showing up all at once after a long wait. That's not just a visual nicety — it makes the app feel dramatically faster, even though the total time to finish the response …

Why AI Benchmarks Don't Always Predict Real-World Performance

Posted on Fri 25 September 2026 in GenAI • Tagged with GenAI, LLM, benchmarks, model-evaluation, opinion

Why I'm Writing This

Every new model release comes with a wall of benchmark charts — MMLU, HumanEval, GPQA, some new benchmark nobody had heard of six months ago — all showing the new model beating the old one by a few percentage points. And yet, plenty of people who actually use …

What Happens to Your Data When You Use an AI Chatbot?

Posted on Thu 24 September 2026 in Beginner Guide • Tagged with GenAI, LLM, privacy, data-security, beginner

Why This Matters

Most people paste things into ChatGPT or Claude without a second thought — a draft email, a piece of code, sometimes even sensitive personal or company information. It's easy to treat it like a private notepad. But understanding what actually happens to that data behind the scenes changes …

Why Some Prompts Work Perfectly in Testing and Fail in Production

Posted on Wed 23 September 2026 in GenAI • Tagged with GenAI, LLM, prompt-engineering, production, testing

Why This Keeps Happening

You spend hours refining a prompt. You test it with ten, twenty, fifty example inputs. It works beautifully every time. You ship it. A week later, real users start hitting it with inputs you never imagined, and the same prompt that felt bulletproof starts producing broken …

The Difference Between an AI That's Wrong and an AI That's Lying

Posted on Tue 22 September 2026 in GenAI • Tagged with GenAI, LLM, hallucination, AI-safety, beginner

Why This Distinction Matters

"The AI lied to me" is something I hear constantly — from beginners, from frustrated users, even in headlines about AI news. It's an understandable way to describe the experience of getting a confidently wrong answer. But the more I looked into how these errors actually happen …

Why The AI Agent Keeps Doing the Same Wrong Thing Twice

Posted on Sun 20 September 2026 in GenAI • Tagged with GenAI, AI-agents, debugging, memory, beginner

Why This Happens to Almost Everyone

If you've built or even just used an AI agent for anything beyond a single simple task, you've probably watched it fail at something, then immediately try the exact same failed approach again — sometimes two or three times in a row — instead of learning …

Will Every App Eventually Have a Built-In AI Agent?

Posted on Sat 19 September 2026 in GenAI • Tagged with GenAI, AI-agents, opinion, product-trends, software

Why I'm Asking This

Open almost any app update log right now and there's a good chance you'll see some version of "meet your new AI assistant" tucked in there. Email clients, project management tools, spreadsheets, note-taking apps, even camera apps — the built-in AI agent has become the default feature …

Why Your Chunks Overlap — and Why That's Actually Intentional

Posted on Fri 18 September 2026 in Beginner Guide • Tagged with GenAI, RAG, chunking, vector-database, beginner

Why This Matters

If you've built even a basic RAG pipeline, you've probably run into "chunk overlap" as a setting — usually with some default value like 50 or 200 tokens — and wondered why you'd deliberately want the same text to appear in two different chunks. Doesn't that just waste storage …

Why Do Different LLMs Give Different Answers to the Same Question?

Posted on Thu 17 September 2026 in Beginner Guide • Tagged with GenAI, LLM, model-comparison, beginner, training-data

Why This Matters

Ask ChatGPT, Claude, and Gemini the exact same question, and you'll often get three noticeably different answers — different structure, different tone, sometimes even different facts or conclusions. As a beginner, this used to confuse me. If they're all "AI," shouldn't they all just... know the same things …

Older Posts