<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Amar Harolikar]]></title><description><![CDATA[Applied Generative AI (Gen AI) for analytics, data science and business. ]]></description><link>https://amarharolikar.wixsite.com/tigzig/blog</link><generator>RSS for Node</generator><lastBuildDate>Sat, 04 Apr 2026 13:51:05 GMT</lastBuildDate><atom:link href="https://amarharolikar.wixsite.com/tigzig/blog-feed.xml" rel="self" type="application/rss+xml"/><item><title><![CDATA[DuckDB isn't just fast SQL. It's Python, SQL and compression all in one box.]]></title><description><![CDATA[I thought DuckDB was fast SQL with great compression. Speeds are lightning fast - I was happy with that. Then I went through  Jasja De Vries 's 30-day DuckDB series. Day by day. All 30. Turns out I was using maybe 10% of what it can do. My analyst and data scientist friends,  DuckDB  isn't just fast SQL. It's Python, SQL and compression all in one box. Here're some features I didn't know existed: ▸ SELECT  EXCLUDE - SELECT  EXCLUDE (col1, col2) - grab everything except specific columns. SQL...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/duckdb-isn-t-just-fast-sql-it-s-python-sql-and-compression-all-in-one-box</link><guid isPermaLink="false">6937e73f9086d1c9fad4530b</guid><pubDate>Tue, 09 Dec 2025 09:12:08 GMT</pubDate><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[The xlwings Lite AI Coder Instruction File - December 2025 Release]]></title><description><![CDATA[xlwings Lite turns Excel into a live Python app. No Python install on the user's machine. Just a browser-based add-in with code editor, console, and deep Excel integration. It launched earlier this year and I've been using it ever since. When you use AI coders like Claude, Cursor, or Gemini to write xlwings Lite code, they don't know its constraints. They generate desktop xlwings syntax that looks right but fails silently. So I started maintaining an instruction file - a document you feed to...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/the-xlwings-lite-ai-coder-instruction-file-december-2025-release</link><guid isPermaLink="false">6935038457f9a8b235205ca6</guid><pubDate>Sun, 07 Dec 2025 04:52:09 GMT</pubDate><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Try Text-to-SQL on Real Data - Multi-Million Rows &#38; GB+ Sizes]]></title><description><![CDATA[Two Clicks. Zero Setup. No Database, No Server, No Login needed. With 9 LLM options, Python &#38; SQL to torture your data till it confesses. App live here: app.tigzig.com/analyzer See PDF for step-by-step guide What's New I've enhanced the sample datasets in my Database AI app (DATS-4). Previously, the test files were tiny, 50-60 rows. Now there's a full range: 64 rows to 11.8 million rows. File sizes from 14 KB to 1.6 GB. For the 1.6 GB file, setup takes around 9 minutes. Fully automated:...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/try-text-to-sql-on-real-data-gb-files-multi-million-rows</link><guid isPermaLink="false">6932b606a7a4d87bcf157b9a</guid><pubDate>Fri, 05 Dec 2025 10:53:24 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/ef0c19_aa27c441863b4bf69ed4b85a014ab325~mv2.png/v1/fit/w_1000,h_1000,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Think about it. One of the world's top AI researchers is building tools. Deploying them live.]]></title><description><![CDATA[Andrew Ng released an 'Agentic Reviewer' for research papers. Started it as a weekend project.   Think about it. One of the world's top AI researchers is building tools. Deploying them live.   That report you keep generating manually. That dashboard someone keeps asking for. That AI app idea you've been 'meaning to build'.  Why aren't you?   The barrier is gone. AI coders (Claude Code, Cursor) turned domain experts into builders. In Andrew's own words "I've long been fan of Claude Code"…  ...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/think-about-it-one-of-the-world-s-top-ai-researchers-is-building-tools-deploying-them-live</link><guid isPermaLink="false">692e6b1b0170a61543011a9b</guid><pubDate>Tue, 02 Dec 2025 04:30:40 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/ef0c19_a75e097c82e84a918b7842fb98333638~mv2.png/v1/fit/w_1000,h_1000,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Gold up 2.3X past 2 years. But what about the 10 years drawdown in between. ]]></title><description><![CDATA[As Buffett says "As “bandwagon” investors join any party, they create their own truth - for a while"   If you had bought it at it previous rising tide (like now) in 2011 you would be waiting for nearly 10 years till 2020 just for it to reach your buying levels.   If it happens again - and it could - do you have the stomach to wait till 2035 or beyond?   Gold has been on a rise since COVID. Central banks loading up, especially emerging markets after the U.S. froze Russian assets. Goldman Sachs...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/gold-up-2-3x-past-2-years-but-what-about-the-10-years-drawdown-in-between-as-buffett-says</link><guid isPermaLink="false">692e61c4724244a5fa6d25b3</guid><pubDate>Tue, 02 Dec 2025 03:51:26 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/ef0c19_73cae4873d7d416c9f62c955372d148a~mv2.png/v1/fit/w_1000,h_1000,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Andrew Ng is using Claude Code, OpenAI Codex, Gemini CLI.]]></title><description><![CDATA[My analyst and data scientist friends - are you?   And no, I don't mean copy-pasting from ChatGPT. I mean Claude Code, Cursor, Gemini CLI - the agentic AI coding tools.   What they let you do: Build full analytics apps. React frontends, database backends, multi-user dashboards. Deploy on your company VPN or bundle as single-file HTML. Go way beyond Excel/VBA. Large codebases get done many times faster. Even for ML model work, Mito AI works inside Jupyter - proper agentic iteration.   I've...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/andrew-ng-is-using-claude-code-openai-codex-gemini-cli</link><guid isPermaLink="false">692e60d15602d55b6723a5aa</guid><pubDate>Tue, 02 Dec 2025 03:46:07 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/ef0c19_3f0a7e8087b74cffab39e5375c8c79a0~mv2.png/v1/fit/w_1000,h_1000,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Bitcoin Down nearly 30% in 25 days. What Does AI Technical Analysis Say?]]></title><description><![CDATA[Get a technical analysis report from my quants agent at: quants.tigzig.com   Open Source. Free. Prompt: 'Run technicals for Bitcoin' You get the report - daily and weekly charts with AI analysis and outlook.   Default model is Gemini 2.5 Flash (~30-45 seconds). Want a deeper analysis? Ask the agent to switch to GPT 5.1 or Claude Sonnet 4.5 or any of the other models. Trade-off: premium models take 2-4 minutes but catch more patterns. Need different timeframes? Just ask the agent to modify.  ...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/bitcoin-down-nearly-30-in-25-days-what-does-ai-technical-analysis-say</link><guid isPermaLink="false">692e5ede5602d55b6723a1ea</guid><pubDate>Tue, 02 Dec 2025 03:39:36 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/ef0c19_54058c6a45c24bed8c4c4de481e5fb3d~mv2.png/v1/fit/w_1000,h_1000,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[[ENHANCEMENT] AI Technical Analysis Now Supports Multiple LLM Choices]]></title><description><![CDATA[Go to quants-suite.tigzig.com   Enter Yahoo Finance symbol, choose time frames, pick your LLM.   You get a technical analysis report with daily and weekly charts (price, volume, technicals) with AI analysis and outlook - PDF and HTML format. I use this as a 2nd opinion against my own analysis.   LLM choices: Fast tier (~30 seconds): Gemini 2.5 Flash/Lite Mid tier (~1 min): GPT 4.1/Mini/Nano, Haiku 4.5 Premium tier (2-5 mins): GPT 5.1, Claude Sonnet 4.5   The time-quality tradeoff: All models...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/enhancement-ai-technical-analysis-now-supports-multiple-llm-choices</link><guid isPermaLink="false">692932019d72494dae9cd7bb</guid><pubDate>Fri, 28 Nov 2025 05:25:07 GMT</pubDate><enclosure url="http://youtu.be/nLUoS_l0KRo" length="0" type="video"/><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Segment 1M customers from 10M transactions (640MB CSV) with natural language queries / Text-to-SQL - entirely in your browser. No server. No remote database. No IT approvals.]]></title><description><![CDATA[Process multi-GB files, build datamarts, and run AI-powered analysis entirely in your browser with DuckDB + text-to-SQL AI. When server deployment isn't an option - or will take 6 months and $1M in approvals - this runs off a single HTML file on your laptop. DABX-1 (Database AI, Browser, eXtended) - built on SQL Rooms (sqlrooms.org) by Ilya Boyandin, customized for analytics workflows that need to move fast without infrastructure headaches. Live at app.tigzig.com/sql-rooms. Or download the...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/run-advanced-analytics-locally-in-your-browser-no-server-no-remote-database-no-it-approvals</link><guid isPermaLink="false">69269ec58fab50c3b6a26189</guid><pubDate>Wed, 26 Nov 2025 06:57:31 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/ef0c19_26f12f145f344dafb1b79d5dbf80df9b~mv2.png/v1/fit/w_1000,h_620,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Google Antigravity just launched. For analysts and data scientists: Worth adding to your toolkit]]></title><description><![CDATA[Google Antigravity just launched. For analysts and data scientists: If you're already on Cursor/Claude Code, this gives you an extra option when you hit message limits. If you're just starting with AI coders, this is the easiest entry point I've seen.   Free agentic IDE with Gemini 3 Pro, Claude Sonnet 4.5, and GPT-OSS built in. Built on top of VS Code. One-click install with pretty good rate limits.   I've been testing it for low &#38; medium complexity tasks. Solid performance so far. Interface...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/google-antigravity-just-launched-for-analysts-and-data-scientists-worth-adding-to-your-toolkit</link><guid isPermaLink="false">6924692c9745b3c9f142ee74</guid><pubDate>Mon, 24 Nov 2025 14:18:43 GMT</pubDate><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[" .  .  -   &#38;  ..."]]></title><description><![CDATA[" .  .  -   &#38;  past 15 ,  . &#38; 500,  &#38;    ." That's the prompt.   Pass it on to my Quants Agent at quants.tigzig.com Get the full report pack: PDF, HTML and CSV for offline analysis.   Be patient. Takes around 2 mins to generate the full set.   - What you get: Security Performance Report...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/execute-asap-approval-granted-google-vs-microsoft-meta</link><guid isPermaLink="false">6922c90a644344a47712cee3</guid><pubDate>Sun, 23 Nov 2025 08:49:23 GMT</pubDate><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Gemini 3 Pro Added to Database AI Suite. Tested Against Claude Sonnet 4.5 and GPT-5.1.Results: Claude still leads. GPT-5.1 is solid. Gemini 3 Pro lands third.]]></title><description><![CDATA[Gemini 3 Pro Added to Database AI Suite. Tested Against Claude Sonnet 4.5 and GPT-5.1. Results: Claude still leads. GPT-5.1 is solid. Gemini 3 Pro lands third. ▪️ Performance Scores Multi-step database analysis workflows: Claude Sonnet 4.5: 115 GPT-5.1: 100 Gemini 3 Pro: 90 90-tier: Gemini 2.5 Pro, GPT-4.1, KIMI 2 Thinking 85-tier: Gemini 2.5 Flash, Qwen 3 Max, GLM 4.6, DeepSeek R1 80-tier: Gemini 2.0 Flash ▪️ Model Findings - Claude Sonnet 4.5: Creates multiple segmentation variables beyond...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/gemini-3-pro-added-to-database-ai-suite-tested-against-claude-sonnet-4-5-and-gpt-5-1-results-claud</link><guid isPermaLink="false">691fee4935662176f69a2e75</guid><pubDate>Fri, 21 Nov 2025 04:56:27 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/ef0c19_e17e736acee842c0a2b911a91846456b~mv2.png/v1/fit/w_1000,h_1000,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Two models added to Database AI Suite this week: GPT-5.1 and KIMI 2 Thinking. ]]></title><description><![CDATA[Two models added to Database AI Suite this week: GPT-5.1 and KIMI 2 Thinking. KIMI 2 Thinking is close to Gemini 2.5 Flash in quality. Costs are higher and more volatile. GPT-5.1 is 20% cheaper than GPT-5 for database execution. Token bloat is down. Default reasoning set to none instead of medium. For advanced analysis planning (single API call, reasoning step): → Gemini 2.5 Flash: strong quality, predictable costs → KIMI 2: similar quality, cost are higher and more volatile → GPT-5.1: high...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/two-models-added-to-database-ai-suite-this-week-gpt-5-1-and-kimi-2-thinking</link><guid isPermaLink="false">691c6be5f5f6788e899ca1c4</guid><pubDate>Tue, 18 Nov 2025 12:54:23 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/ef0c19_e9bb0b27e5624f6bad07eda0cee3bd34~mv2.png/v1/fit/w_1000,h_1000,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Bundle your AI app or React dashboard into a single file. ]]></title><description><![CDATA[Bundle your AI app or React dashboard into a single file. No AWS. No Vercel. No IT approvals. The entire app - all code, visualizations, database engine - in one file.  Download it. Email it. Share it on a drive. Double-click to open. It works.  Practical applications - Build and share AI &#38; automation apps in small teams. - Send a prospect a working prototype instead of PowerPoint. They load their data, click around, experience it. - Quarterly dashboards for leadership without Power BI...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/bundle-your-ai-app-or-react-dashboard-into-a-single-file</link><guid isPermaLink="false">691c6b1af5f6788e899ca062</guid><pubDate>Tue, 18 Nov 2025 12:50:19 GMT</pubDate><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[AI Coders are here. The edge now is domain + execution. Not vibing.]]></title><description><![CDATA[Three perspectives. All pointing to the same shift. An investor, a strategist, and a hands-on analyst.  Vibing? Get this straight - there is no vibe magic going on here. Prompt hot air into a chat box and out pops a production level model / app - doesn't work that way.  The Investor's View Francois Arbour (founder, sold to Shutterstock): The 10x lie. Developers are building solutions in search of problems. Now doing it 10x faster. The real multiplier isn't in your IDE. It's understanding...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/ai-coders-are-here-the-edge-now-is-domain-execution-not-vibing</link><guid isPermaLink="false">691c69f1b8e90ba7de37d8fd</guid><pubDate>Tue, 18 Nov 2025 12:45:13 GMT</pubDate><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[The Google Machine continues to roll. Will it do to AI what it did to search?]]></title><description><![CDATA[A month ago, I posted that Google was back in the AI race. Earlier in the year, I wrote about the shift in their LLM quality. Sanya Ojha's analysis this week confirms it from the strategy side. I'm seeing it from the execution side. Google is shipping at a rate I haven't seen in years. Around 20% of my workflow now runs on Gemini. In January 2025, that was 0%. Here's what I am using for my client projects ▸ gemini-2.5-flash-lite - my workhorse. first choice for automations. Fast, great...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/the-google-machine-continues-to-roll-will-it-do-to-ai-what-it-did-to-search</link><guid isPermaLink="false">691c68511f01408bc64427ec</guid><pubDate>Tue, 18 Nov 2025 12:40:05 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/ef0c19_82b1b0c8da894614b8336f799958c47d~mv2.png/v1/fit/w_1000,h_987,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Instant Database Setup for AI Apps. With Neon.com]]></title><description><![CDATA[You're building an AI app. A user hits 'create'. Your app needs to spin up a database. How long do they wait?  Regular cloud databases take 3-5 minutes or longer to setup, need manual configuration, charge 24/7 even when idle. Doesn't work when you need databases created on-demand, within an API call.  I use neon.com for this. Neon setups up a full Postgres instance in under 1 second via API. Not a sandbox. A real database with connection string, credentials, everything.  I use it in my data...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/instant-database-setup-for-ai-apps-with-neon-com</link><guid isPermaLink="false">691c669eb059ba28aed52ff2</guid><pubDate>Tue, 18 Nov 2025 12:31:51 GMT</pubDate><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[AI Coders give you the edge.The 6 Rules I Follow When Working with AI Coders.]]></title><description><![CDATA[Coding by hand is a business liability. AI Coders give you the edge. The 6 Rules I Follow When Working with AI Coders.  This post builds on my earlier one - 'Coding by hand is obsolete' Post | LinkedIn  Over two decades coding by hand in SAS, Python, SQL, VBA - across enterprises and SMBs - and the last two with AI, I’ve reached one conclusion:         . It’s slower, costlier, and less scalable. The P&#38;L edge of...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/ai-coders-give-you-the-edge-the-6-rules-i-follow-when-working-with-ai-coders</link><guid isPermaLink="false">691c61d628e86384d5785f27</guid><pubDate>Tue, 18 Nov 2025 12:24:59 GMT</pubDate><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Coding by hand is becoming obsolete - Andrew Ng. I disagree.]]></title><description><![CDATA[It already is. Andrew is just being polite. (Post link below) After 25 years of writing code line by line, I now execute everything with AI Coders. Claude Code, Cursor, and Gemini CLI are my day-to-day tools. AI does the coding, but I still review, explain, and learn from it. The buck stops with me. ▪ The speed of execution is huge. But's that's just one part of it. It’s about what can now be done. My pre-AI world was limited to SAS, Python, Excel, SQL and ML models. Projects I once declined...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/coding-by-hand-is-becoming-obsolete-andrew-ng-i-disagree</link><guid isPermaLink="false">690aefc9988cdeb684f7a89a</guid><pubDate>Wed, 05 Nov 2025 06:34:38 GMT</pubDate><dc:creator>Amar Harolikar</dc:creator></item><item><title><![CDATA[Intelligent AI Web Scraper in Excel with Python (xlwings Lite)]]></title><description><![CDATA[Tell it what to extract - fields, filters, rules - all in plain English. Live Tool. Paste a URL list. The app extracts the fields you asked for, applies your transforms, filters and any data cleaning instructions. And updates structured data in Excel, URL status, error logs, and a 30-KPI scraping dashboard. ▪ What Intelligence does You can share instructions in conversational English. Filter: 'Don't include any records from Mumbai, Chennai and Delhi' Select: 'If there are multiple phone...]]></description><link>https://amarharolikar.wixsite.com/tigzig/post/intelligent-ai-web-scraper-in-excel-with-python-xlwings-lite</link><guid isPermaLink="false">69086dfbb590340bf5d53d47</guid><pubDate>Mon, 03 Nov 2025 08:57:18 GMT</pubDate><enclosure url="https://static.wixstatic.com/media/ef0c19_13de74fb48054981af8505551bfef87e~mv2.png/v1/fit/w_1000,h_1000,al_c,q_80/file.png" length="0" type="image/png"/><dc:creator>Amar Harolikar</dc:creator></item></channel></rss>