@shivamshasheesh

How I Replaced My $20/Month Claude Subscription With Gemma 4 Running Locally Through Ollama

Apr 4 · 11 min read · How I Replaced My $20/Month Claude Subscription With Gemma 4 Running Locally Through Ollama I canceled my Claude Pro subscription last week. Not because Claude got worse — it didn't. I canceled because Google released Gemma 4, Ollama added native Cla...

Building Semantic Search Over Automotive AUTOSAR Configurations — How I Made 1000+ XML Parameters Queryable in Natural Language

Feb 10 · 6 min read · Building Semantic Search Over Automotive AUTOSAR Configurations Automotive embedded software is built on AUTOSAR — an industry-standard architecture that defines how ECU software components communicate, manage memory, handle diagnostics, and schedule...

Google Stitch + MCP Server Changed How I Design UI — Here's My Full Workflow

Dec 15, 2025 · 9 min read · Google Stitch + MCP Server Changed How I Design UI — Here's My Full Workflow I'm not a designer. I'm a software engineer who's spent the last three years building enterprise platforms — RAG pipelines, AUTOSAR tooling, FastAPI backends, Angular dashbo...

I Built a Production-Grade RAG Framework With Hybrid Search, Contextual Chunking, and Zero Cloud Lock-In

Oct 20, 2025 · 9 min read · I Built a Production-Grade RAG Framework With Hybrid Search, Contextual Chunking, and Zero Cloud Lock-In Every RAG tutorial on the internet follows the same pattern: take a document, split it into 512-token chunks, embed with OpenAI, dump into a vect...