Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Cursor .cursorrules and MCP Services
Learn to use Cursor’s Agent Mode, configure .cursorrules with JSON, leverage Notepads, and integrate Model Context Protocol services for larger projects.
At the last AI tinkerers, I was convinced by another attendee to switch IDEs from VSCode to Cursor. Since then I’ve been learning how to get the most from Cursor and want to share several of my findings.
1) Agent Mode - Cursor’s superpower (but now in Co-Pilot)
- Quick basics - how to use it, how is composer + agent (+ yolo?) different from chatting.
- how to get agent mode to work better - context, @
2) Building / working with larger projects, frameworks like NextJS - The .cursorrules file - why you should have one in all your projects
- The FORMAT matters - markdown is not best! JSON is better
- Several repositories for best practice cursor rules files. - Notepads - what happens when you do and don’t use these.
- Model Context Protocol servers and services and when/why you would use these while developing
3) Time permitting - the AI Secretary .cursorrules file - going beyond coding in Cursor
- CursorThe AI-native code editor designed for high-velocity development through deep LLM integration.Cursor is a fork of VS Code that embeds AI directly into the development workflow while maintaining full extension compatibility. It leverages models like Claude 3.5 Sonnet and GPT-4o to power features such as Cmd+K for inline edits and Cmd+L for codebase-wide chat. By indexing local files, Cursor provides precise context for its predictive 'Tab' completions and multi-file 'Composer' mode. This setup allows engineers to move from high-level intent to functional code without leaving the editor or losing context.
- NextNext.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.
- GitHub CopilotGitHub Copilot is your AI pair programmer, delivering real-time code suggestions, generating unit tests, and summarizing pull requests directly in your IDE.GitHub Copilot acts as your generative AI pair programmer, accelerating development by suggesting lines and entire functions in real time, often appearing as 'ghost text' directly in your IDE (VS Code, Visual Studio, JetBrains IDEs). Leveraging models like GPT-4.1, it moves beyond simple completions: developers use Copilot Chat for complex tasks like generating unit tests, explaining code, or using Copilot Edits to make changes across multiple files from a single natural language prompt. This tool integrates deeply into the workflow, from code creation to AI-generated pull request summaries, significantly boosting developer productivity.
Related projects
Capture, search and learn from each AI coding journey
DC
The talk demonstrates how SpecStory Cursor automatically saves Composer chat logs, creates versioned .cursorrules, and enables searchable histories…
DocRouter.AI
Boston
We'll demonstrate how DocRouter.AI extracts full schemas from unstructured documents using a drag‑and‑drop UI, and how the Cursor…
AI Fundamentals and Best Practices
Boston
An overview of AI fundamentals, practical tips for using ChatGPT and Co‑Pilot, and real‑world examples to help beginners…
AI "copilot" for Jupyter notebook
Boston
Learn how to integrate an Ollama LLM as a Jupyter notebook copilot using Docker Compose, enabling interactive code…
The next evolution of AI - Neurosymbolic
London
Demonstration of a lightweight neurosymbolic platform that maps data, lets you define business logic in plain English, and…
The Personal AI Assistant: When Cursor Meets Claude Code for Life Management
Waterloo
Learn how to build a personal AI assistant with Cursor and Claude Code that tracks goals, automates routines,…