# Prasham H Trivedi > Software your way. Finally affordable. Finally fast. I install one running piece of software on your stack (Cloudflare Workers, MCP, serverless), then keep it. This file follows the llms.txt convention (https://llmstxt.org) - a curated index of high-signal pages for Large Language Models retrieving content from this site. ## Pillar Posts The posts below are the canonical entry points to the writing. Each is hand-selected as representative of how I think and what I ship. - [MCP transports, decided](https://prashamhtrivedi.in/mcp-transports-decided/) - MCP transport choice, decided: stdio for local, Streamable HTTP for remote, SSE deprecated. The ten-second rule plus the stdout gotcha that costs you an afternoon. - [No, MCP servers aren't dead (and here's the 2007 reason why)](https://prashamhtrivedi.in/mcp-isnt-dead/) - MCP isn't dead. The 'MCP is dead' wave measures the wrong axis: update friction. MCPs auto-fetch the maintainer's latest; skills default to download-and-own. - [Mobile won the platform war on distribution, not capability](https://prashamhtrivedi.in/mobile-lost-on-distribution/) - Mobile didn't beat the web on capability. It beat the web on the channel. A platform-war retrospective on distribution, store lock-in, and update friction. - [Three Commands, Four Documents: The AI Workflow That Actually Ships](https://prashamhtrivedi.in/plan-execute-verify-workflow/) - The Plan-Execute-Verify workflow that replaced my 13-document nightmare. Three commands, complexity scoring, and the failure modes to watch for. - [AI Agent Workflow: 13 Documents for a Label Change](https://prashamhtrivedi.in/how-not-to-arrange-ai-workflow/) - A satirical anti-guide to AI agent workflows. Learn how to fail spectacularly by treating AI agents like a 2022 dev team. Conway's Law meets subagent chaos. - [Gemini 3 Pro vs GPT 5.2: A Blind Test Reveals Code Red DNA](https://prashamhtrivedi.in/code-red-dna-model-comparison/) - Blind A/B test: Gemini 3 Pro vs GPT 5.2. Same prompt, same input. Gemini produced 60 surgical lines; GPT produced 250 bloated lines. Training beats prompts. - [Your AI Agent Config is Technical Debt You Haven't Acknowledged Yet](https://prashamhtrivedi.in/agent-config-technical-debt/) - Your AI agent configuration is technical debt. From slash commands to skills, our prompts haven't evolved with the models. Time to audit your config. - [Three AI Agents Walk Into a Bar (and Only One Actually Read the Menu)](https://prashamhtrivedi.in/ai-agent-comparison-claude-gemini-codex/) - Real-world comparison of Claude Code, Gemini, and Codex AI coding agents tested on writing style analysis. Claude scored 9.5/10, Codex 7.5/10, Gemini 7.5/10. Configuration matters as much as capability. - [Shopify & WooCommerce AI Automation: Complete E-commerce Integration Case Study](https://prashamhtrivedi.in/case-studies/shopify-woocommerce-ai-automation-case-study/) - I installed Shopify and WooCommerce AI automation on the client's own Cloudflare stack: MCP, Workers, webhooks. Ten to fifteen days, then I kept it. - [Rebuilding Invoice System with AI: A 48-Hour Journey](https://prashamhtrivedi.in/post/rebuilding_invoice_system/) - Leveraged LLMs to rebuild our invoice system in 48 hours. Explores AI-driven development, prompt engineering, and lessons learned from this rapid migration. - [Serverless Invoice Management System with AWS](https://prashamhtrivedi.in/invoicer/) - Revolutionized invoice management with a serverless system using AWS Lambda, S3, DynamoDB, and Anthropic API. Reduced a hours-long task to 5 minutes. - [LLM Development Lessons: Tools, Tips, and Tricks](https://prashamhtrivedi.in/llm_dev_lessons/) - A developer's journey through LLM-powered development tools. Shares favorite tools, reasons for skipping others, and 8 battle-tested tips for LLM coding. - [API Design: Share Specs, Not Execution](https://prashamhtrivedi.in/share-specs-not-execution/) - Discusses the importance of sharing API specifications (Swagger/OpenAPI) over execution details (Postman collections) for better collaboration and avoiding issues. - [Introducing Sourcesailor](https://prashamhtrivedi.in/introducing_sourcesailor.html) - SourceSailor is a CLI that helps anyone understand a codebase with the help of LLMs. This post introduces the tool, the features and tells the story how it came to be. ## Surface Map - Home: https://prashamhtrivedi.in/ - About: https://prashamhtrivedi.in/about/ - Projects: https://prashamhtrivedi.in/projects/ - All posts: https://prashamhtrivedi.in/posts/ - Pillar posts (curated): https://prashamhtrivedi.in/pillars/ ## External Surfaces (same entity, different buyers) - GitHub: https://github.com/PrashamTrivedi - LinkedIn: https://www.linkedin.com/in/prasham-trivedi-71521724/ - prashamhtrivedi.app (separate Gujarati SMB surface, not this site's pitch) ## Contact - Email: me@prashamhtrivedi.in --- Generated by Hugo from posts marked `pillar: true` in front-matter. To suggest a missing post, open an issue at https://github.com/PrashamTrivedi/PersonalSite.