---
title: "Shivam Shasheesh (@shivamshasheesh) | Hashnode"
description: "shows reflection, not just execution. Read the latest articles by Shivam Shasheesh on Hashnode."
url: "https://hashnode.com/@shivamshasheesh"
---

@shivamshasheesh

# Shivam Shasheesh

@shivamshasheesh · Hyderabad, India · Joined April 2026

shows reflection, not just execution

### [How I Replaced My $20/Month Claude Subscription With Gemma 4 Running Locally Through Ollama](https://shivamshasheesh.hashnode.dev/replaced-claude-subscription-gemma-4-ollama-local-ai?utm_source=hashnode&utm_medium=feed)

Using ollama launch claude with Gemma 4 for zero-cost agentic AI coding — full setup, capabilities deep-dive, and honest review

11 min read · [shivamshasheesh.hashnode.dev](https://shivamshasheesh.hashnode.dev/replaced-claude-subscription-gemma-4-ollama-local-ai?utm_source=hashnode&utm_medium=feed)

[Apr 4](https://hashnode.com/posts/replaced-claude-subscription-gemma-4-ollama-local-ai/69d17ebb96ce10a118b43bdb)

### [Building Semantic Search Over Automotive AUTOSAR Configurations — How I Made 1000+ XML Parameters Queryable in Natural Language](https://shivamshasheesh.hashnode.dev/semantic-search-autosar-arxml-rag-faiss?utm_source=hashnode&utm_medium=feed)

Designing an ETL + RAG pipeline to parse complex ARXML schemas, generate 3072-dim embeddings, and answer engineering questions about ECU configs instantly

6 min read · [shivamshasheesh.hashnode.dev](https://shivamshasheesh.hashnode.dev/semantic-search-autosar-arxml-rag-faiss?utm_source=hashnode&utm_medium=feed)

[Feb 10](https://hashnode.com/posts/semantic-search-autosar-arxml-rag-faiss/69d181a92197fc5a1006f98e)

### [Google Stitch + MCP Server Changed How I Design UI — Here's My Full Workflow](https://shivamshasheesh.hashnode.dev/google-stitch-mcp-server-ai-ui-ux-design-workflow?utm_source=hashnode&utm_medium=feed)

Using Stitch's AI-native canvas and MCP server to go from natural language to production-ready UI designs in minutes

9 min read · [shivamshasheesh.hashnode.dev](https://shivamshasheesh.hashnode.dev/google-stitch-mcp-server-ai-ui-ux-design-workflow?utm_source=hashnode&utm_medium=feed)

[Dec 15, 2025](https://hashnode.com/posts/google-stitch-mcp-server-ai-ui-ux-design-workflow/69d185dcd145887b5e1a8466)

### [I Built a Production-Grade RAG Framework With Hybrid Search, Contextual Chunking, and Zero Cloud Lock-In](https://shivamshasheesh.hashnode.dev/ragpipe-production-rag-framework-hybrid-search-contextual-chunking?utm_source=hashnode&utm_medium=feed)

How ragpipe combines BM25 + dense vectors, Anthropic's contextual retrieval, HyDE query expansion, and Ollama-first local inference into a modular Python framework

9 min read · [shivamshasheesh.hashnode.dev](https://shivamshasheesh.hashnode.dev/ragpipe-production-rag-framework-hybrid-search-contextual-chunking?utm_source=hashnode&utm_medium=feed)

[Oct 20, 2025](https://hashnode.com/posts/ragpipe-production-rag-framework-hybrid-search-contextual-chunking/69d188b2231cb87d2b81219c)