Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
I Don't Write Code: How a Truck Parts Wholesaler Runs on 80 AI Skills and 5 Agents
See how 80 AI skills and 5 agents run a B2B truck parts wholesaler, including code generation, competitor scraping, and a verification gate.
I built the agentic system that runs a B2B heavy-duty truck parts wholesaler — a dealer mobile app on a BigCommerce backend, a competitor price-intelligence scraper, dealer analytics, and 80 purpose-built Claude Code skills plus 5 specialized subagents gluing it together. I’m not a software engineer. Agents write every line of code; my job is directing and verifying it, which is why verification ended up being the architecture instead of an afterthought.
Live on screen, three systems:
- The arsenal — how 80 skills and 5 subagents are structured, how one gets invoked, and the counterargument agent whose only job is attacking my conclusions before I act on them.
- The business pipelines — scraping a login-gated competitor B2B portal to diff catalog and pricing against ours, and pulling live BigCommerce data to answer questions like which dealers went quiet this month.
- The verification gate — a Stop hook that runs typecheck and the test suite on every code change and blocks the agent from ending its turn on a failure. I’ll break something on purpose and let it catch me.
Real store, real dealers, real orders. Code, logs, and architecture on screen. No slides.
- Claude Code (Opus)Claude Code Opus is a terminal-based agentic tool that pairs Anthropic’s most intelligent model with direct filesystem access to automate complex engineering tasks.Claude Code Opus transforms software development from manual tinkering into an industrial-scale process by combining the Claude Opus 4.6 model with a command-line interface. Unlike standard chat assistants, this agentic duo reads and writes files directly, executes terminal commands, and manages multi-step refactoring across massive codebases using a 1-million-token context window. It eliminates manual context-pasting by maintaining a local CLAUDE.md memory file and offers an effort parameter (low, medium, high) to balance deep reasoning with token efficiency. Engineers use it to find zero-day vulnerabilities, debug production environments in a loop, and delegate high-stakes planning that previously required constant human oversight.
- BigCommerce GraphQLBigCommerce GraphQL provides a powerful, flexible API for storefront data access.BigCommerce GraphQL offers a robust API (Application Programming Interface) for developers to interact with storefront data. It enables precise data fetching, reducing over-fetching and under-fetching common with traditional REST APIs. This allows for highly customized and performant storefront experiences, giving developers the tools to build innovative solutions on the BigCommerce platform.
- PlaywrightPlaywright is the Microsoft-developed, cross-browser automation framework: it drives Chromium, Firefox, and WebKit with one unified API for fast, reliable end-to-end testing.Playwright delivers robust, cross-platform end-to-end testing, supporting all major rendering engines: Chromium, Firefox, and WebKit. Launched by Microsoft in January 2020, its core strength is a single API for multiple languages (TypeScript, Python, Java, .NET). The framework eliminates flaky tests through automatic waiting and provides full test isolation by creating a new browser context (a brand-new browser profile) for each test. Key tooling includes Codegen for recording actions and the Trace Viewer for deep post-mortem analysis of test failures (screencasts, live DOM snapshots). This architecture ensures reliable, high-speed execution across Windows, Linux, and macOS.
- React NativeReact Native is an open-source framework for building native mobile applications (iOS, Android) using JavaScript and React.React Native is a powerful JavaScript framework, originally developed by Meta (Facebook), enabling developers to build truly native mobile applications for both iOS and Android from a single codebase. It utilizes the React declarative programming model and bridges JavaScript code to the native UI components of each platform, ensuring high performance and a genuine native look and feel. This approach allows teams to share up to 90% of code, drastically reducing development time and cost. Major companies like Facebook, Microsoft, and Shopify leverage React Native for their production apps, validating its scalability and efficiency for cross-platform development.
- GitHub ActionsGitHub Actions automates your software workflows (CI/CD, testing, deployment) directly within your repository.GitHub Actions is your native, event-driven automation platform: it executes custom workflows right inside your GitHub repository. Define multi-step jobs using YAML files, which must be stored in the `.github/workflows` directory. These workflows trigger on specific events, like a `push` to a branch or a `pull_request` opening. The platform supports world-class Continuous Integration and Continuous Deployment (CI/CD), letting you build, test, and deploy code across any language (e.g., Python, Node.js, Java). Runners—Linux, Windows, or macOS virtual machines—execute the jobs. For security, confidential data is managed via GitHub `secrets`, ensuring credentials stay out of your code.
Related talks
More from the community
Jules: An AI Agent That Thinks, Argues, and Writes
Austin
The Store That Runs Itself (and the Agent That Manages My Employee)
Atlanta
See an e-commerce store run entirely by code, from product rendering to order fulfillment, managed by an agent…
Built a Browser Game With a Team of AI Agents, and Here's Everything That Broke
Dubai
See how a browser RPG was built using AI agents. Discover the real-world challenges, surprising failures, and lessons…
Building Agentic OS for Marketing
Denver
Learn how to build an AI-native consultancy, running all business tasks through AI agents and deploying live client-facing…
The Interview That Runs Itself
Seattle
Watch a Governed Multi-Agent System Block, Verify, and Replay AI Code — Live
Montreal
See a live demo of aming-claw, a system that lets AI agents write code under enforced contracts, including…
Compose Email
Loading recent emails...