shelf: autoresearch for Shopify storefronts | Toronto .

Members-Only

Recent Talks & Demos are for members only

Exclusive feed

You must be an AI Tinkerers active member to view these talks and demos.

April 29, 2026 · Toronto

shelf: autoresearch for Shopify storefronts

This talk explores shelf, an open-source CLI that uses an autoresearch loop to optimize Shopify product catalog AI discoverability by generating shopper queries and iteratively improving product surfacing.

Overview
Links
Tech stack
  • Shopify Admin GraphQL API
    A high-performance interface for managing Shopify store data with precise, single-endpoint queries.
    The Shopify Admin GraphQL API provides developers with granular control over store resources like products, orders, and customers. By utilizing a single POST endpoint, it eliminates the over-fetching common in REST, allowing you to retrieve nested data (such as variants within a specific collection) in one round trip. It supports advanced features like bulk operations for massive datasets and asynchronous mutations to handle high-volume inventory updates. With a stable versioning cycle released every three months, it ensures predictable scaling for apps serving over 1.7 million merchants.
  • OpenAI Responses API
    The unified, stateful API endpoint for advanced model interactions, consolidating the best features of Chat Completions and Assistants.
    The OpenAI Responses API is our most advanced, single interface for generating model outputs (text and image). It unifies the functionality of the Chat Completions and Assistants APIs into one powerful endpoint: `/v1/responses`. This new API natively manages conversation state, eliminating the need for manual history tracking. Crucially, it integrates built-in tools like Web Search, File Search, and Function Calling, enabling models (e.g., GPT-4o) to execute agentic workflows and ground responses with real-time or private data, delivering superior, context-aware results.
  • Claude Sonnet
    Claude Sonnet 4.5 is Anthropic's premier model: state-of-the-art for agentic coding, computer use, and complex, long-horizon workflows.
    Claude Sonnet 4.5 is engineered for superior agentic performance, excelling in complex, multi-step workflows across coding, finance, and cybersecurity (e.g., achieving a 77.2% score on SWE-bench Verified). This model offers a powerful balance of speed and cost: it is priced at $3 per million input tokens and supports a massive 200,000-token context window. This capacity allows for sustained reasoning, with internal tests confirming the model maintains focus for over 30 hours on demanding tasks. It is available via the Claude API, Amazon Bedrock, and Google Cloud's Vertex AI, making it the top choice for developers building robust, production-ready AI agents.
  • Next
    Next.js is the full-stack React framework: it delivers high-performance web applications via hybrid rendering and powerful, Rust-based tooling.
    This is the React Framework for production: Next.js enables you to build full-stack web applications with zero configuration and maximum efficiency. It supports a hybrid rendering approach (Server-Side Rendering, Static Site Generation, and Incremental Static Regeneration) for optimal speed and SEO performance. Key features include React Server Components, Server Actions for running server code directly, and the App Router for advanced routing and nested layouts. Developed by Vercel, it leverages Rust-based tools like Turbopack and the Speedy Web Compiler for the fastest possible builds and a superior developer experience.
  • TypeScript
    TypeScript is an open-source superset of JavaScript: it adds static typing and compiles to clean, standards-based JavaScript.
    TypeScript is a high-level, open-source language developed by Microsoft: it acts as a superset of JavaScript, adding a powerful static type system. This system enables compile-time type checking, catching errors before runtime (a critical benefit for large-scale applications). The TypeScript Compiler (TSC) reliably transpiles all code into clean, standards-based JavaScript (ES3 or newer), ensuring compatibility across any browser or host environment (Node.js, React.js, etc.).