<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel><title>Rajib&#x27;s</title><link>https://blog.rajibsai.com/</link><description>Notes on AI software, hardware and services</description><language>en</language>
  <item><title>Streaming LLM Responses to a React Frontend with Server-Sent Events</title><link>https://blog.rajibsai.com/stream-llm-react-sse/</link><guid>https://blog.rajibsai.com/stream-llm-react-sse/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>A tested Node.js server and fetch-based SSE reader that streams tokens, stops paying for abandoned requests, and plugs into a small React hook.</description></item>
  <item><title>How to Write a Clear README: A Template for Every Repo (and a Linter to Check It)</title><link>https://blog.rajibsai.com/readme-template-for-every-repo/</link><guid>https://blog.rajibsai.com/readme-template-for-every-repo/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>A README template that answers what, why and how in the order readers need, what GitHub does with your README, and a tested Python linter that flags missing sections, untagged code blocks and broken relative links.</description></item>
  <item><title>Prompt Versioning for Small Teams: Keep Prompts in Git, Not in Slack</title><link>https://blog.rajibsai.com/prompt-versioning-git/</link><guid>https://blog.rajibsai.com/prompt-versioning-git/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>A small Node.js pattern for versioned prompt files with strict variables and a content hash in every log line, so you can always answer which prompt produced which output.</description></item>
  <item><title>A Reusable Prompt Snippet Library for Developers: Review, Debug and Document Faster</title><link>https://blog.rajibsai.com/prompt-snippet-library-developers/</link><guid>https://blog.rajibsai.com/prompt-snippet-library-developers/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>Stop retyping the same instructions. Build a small library of prompt snippets with /slash expansion in Node.js, plus how chat tools like Shortcut Chat handle reusable shortcuts.</description></item>
  <item><title>Prompt Injection Basics for Web Developers: What to Defend First</title><link>https://blog.rajibsai.com/prompt-injection-web-developers/</link><guid>https://blog.rajibsai.com/prompt-injection-web-developers/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>A practical priority list for web developers adding LLM features: limit what the model can do, validate tool calls in code, and require confirmation for side effects. Includes a tested tool-call gate.</description></item>
  <item><title>Vector Search Without a Vector Database: When Postgres Is Enough</title><link>https://blog.rajibsai.com/pgvector-vs-vector-database/</link><guid>https://blog.rajibsai.com/pgvector-vs-vector-database/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>When pgvector or even a plain in-memory scan is enough for semantic search, with a runnable demo of the filtered-search trap that returns too few rows and the pgvector 0.8 fix.</description></item>
  <item><title>How to Build a Small Evaluation Set for Your LLM Feature Before You Ship</title><link>https://blog.rajibsai.com/llm-evaluation-set/</link><guid>https://blog.rajibsai.com/llm-evaluation-set/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>Build a 30-case evaluation set, a 40-line runner and a CI check so prompt changes can&#x27;t quietly break your LLM feature. Includes a runnable Node.js example with a baseline file.</description></item>
  <item><title>Cost Control for LLM Apps: Token Budgets, Caching and Per-User Limits</title><link>https://blog.rajibsai.com/llm-cost-control/</link><guid>https://blog.rajibsai.com/llm-cost-control/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>A tested Node.js module that adds a per-user daily token budget and a TTL response cache around any LLM call, plus the habits that keep an AI feature&#x27;s bill predictable.</description></item>
  <item><title>How to Make LLM API Calls Reliable in Node.js: Timeouts, Retries and JSON Validation</title><link>https://blog.rajibsai.com/llm-api-retries-node/</link><guid>https://blog.rajibsai.com/llm-api-retries-node/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>A short, tested Node.js module that adds a hard timeout, backoff with jitter, Retry-After handling and schema-validated JSON to any chat-style LLM API call.</description></item>
  <item><title>Generating PDF Invoices in Node.js: A Small Working Example With Real Tests</title><link>https://blog.rajibsai.com/generate-pdf-invoice-nodejs/</link><guid>https://blog.rajibsai.com/generate-pdf-invoice-nodejs/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>Build a PDF invoice with PDFKit and Node.js: integer-cent money, correct tax rounding, multi-page tables with repeated headers and page numbers, and tests that read the generated PDF back and check the numbers.</description></item>
  <item><title>Writing Documentation Developers Actually Read: Structure, Examples and Changelogs</title><link>https://blog.rajibsai.com/developer-documentation-structure/</link><guid>https://blog.rajibsai.com/developer-documentation-structure/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>Organise developer docs around four reader needs (tutorials, how-to guides, reference, explanation), write examples that run, keep a useful changelog, and check structure and links automatically with a tested audit script.</description></item>
  <item><title>Choosing an LLM for Your Feature: How to Compare Answers Side by Side Before You Write Code</title><link>https://blog.rajibsai.com/compare-llm-answers-side-by-side/</link><guid>https://blog.rajibsai.com/compare-llm-answers-side-by-side/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>A practical, blind-scoring method for choosing between AI models for a real feature, with a tested Node.js scorer, plus where side-by-side chat tools like Shortcut Chat help and where they stop.</description></item>
  <item><title>Using AI Coding Assistants on Solidity Projects: What to Trust and What to Review</title><link>https://blog.rajibsai.com/ai-coding-assistants-solidity/</link><guid>https://blog.rajibsai.com/ai-coding-assistants-solidity/</guid><pubDate>Tue, 17 Nov 2026 00:00:00 +0000</pubDate><description>Where AI-generated Solidity needs human review: tx.origin authorisation, ignored ERC-20 return values, and unchecked upgrade and access assumptions, with failing tests you can run.</description></item>
</channel></rss>
