This is just an initial beta but it works, I saw the MIT paper really useful for analyzing logs and errors. I created the MCP to solve a real pain I have when using AI coders.
Good point, currently if user intent classified as DIY and because it take more time to process the plan and the products, I added a button during process to cancel that will disregard the DIY path and simply return only the products. There is also follow up with context and can update the results and UI as well, but still finetuning these hard turns from DIY to shopping and vice versa.
The Problem: Keyword search fails for complex, multi-item projects. If I want to "build a backyard rink" or "draft-proof my house," I usually end up with 15 tabs open, manually piecing together a shopping list from forums and reviews.
The Solution: I built an intent-based search engine. instead of matching keywords, it converts user prompts into vector embeddings to map broad goals (intents) to specific product clusters.
The Stack:
Backend: node.js/TypeScript
Search: pgvector for semantic similarity (PostgreSQL)
LLM: Orchestrates the "logic" of the project plan and validates compatibility.
The "Microsoft" Context: I actually launched this 24 hours before Microsoft Copilot released their "Shopping Agent." While I can't compete with them on generic "buy a laptop" queries, I’m pivoting to go deep on complex DIY/Hardware projects where context matters more than reach.
Current Status: Currently indexing Amazon (US/CA) with every search. My internal prototype worked perfectly with Canadian Tire (local hardware inventory is much better for DIY than Amazon), and I'm working on deep-linking that next to build better carts.
I’d love feedback on the result relevance. Roast my MVP.