Agentic Engineering for React Teams: Give Your Coding Agent a Map

Today's Talk discusses the future of performance tooling, focusing on user-centric, actionable, and contextual approaches. The introduction highlights Adi Osmani's expertise in performance tools and his passion for DevTools features. The Talk explores the integration of user flows into DevTools and Lighthouse, enabling performance measurement and optimization. It also showcases the import/export feature for user flows and the collaboration potential with Lighthouse. The Talk further delves into the use of flows with other tools like web page test and Cypress, offering cross-browser testing capabilities. The actionable aspect emphasizes the importance of metrics like Interaction to Next Paint and Total Blocking Time, as well as the improvements in Lighthouse and performance debugging tools. Lastly, the Talk emphasizes the iterative nature of performance improvement and the user-centric, actionable, and contextual future of performance tooling.

Kenton Varda advocates for using CapnWeb, an RPC protocol, over REST for web APIs, emphasizing benefits for humans and AI agents. CapnWeb simplifies client-server communications by treating them as function calls. TypeScript type checking ensures method accuracy in CapnWeb across JavaScript runtimes. Stubs in CapnWeb allow method calls to execute on remote objects and simulate all possible method names for remote calls. Converting REST APIs to CapnWeb streamlines code and improves API calls. CapnWeb enhances API functionality with object-specific RPC sessions and promises pipelining for multilevel API optimization. AI agent security challenges are addressed with sandboxing and token protection in CapnWeb. CapnWeb capabilities for AI agents include passing restricted CapnWeb stubs and exploring capability-based security with CapnProto.

Rome is a toolchain built in Rust that aims to replace multiple tools and provide high-quality diagnostics for code maintenance. It simplifies tool interactions by performing all operations once, generating a shared structure for all tools. Rome offers a customizable format experience with a stable formatter and a linter with over 150 rules. It integrates with VCS and VLSP, supports error-resilient parsing, and has exciting plans for the future, including the ability to create JavaScript plugins. Rome aims to be a top-notch toolchain and welcomes community input to improve its work.

Today's Talk explores the complexity in code and its impact. It discusses different methods of measuring complexity, such as cyclomatic complexity and cognitive complexity. The importance of understanding and conquering complexity is emphasized, with a demo showcasing complexity in a codebase. The Talk also delves into the need for change and the role of refactoring in dealing with complexity. Tips and techniques for refactoring are shared, including the use of language features and tools to simplify code. Overall, the Talk provides insights into managing and reducing complexity in software development.

GitHub Copilot is an auto-completion tool that provides suggestions based on context. Research has shown that developers using Copilot feel less frustrated, spend less time searching externally, and experience less mental effort on repetitive tasks. Copilot can generate code for various tasks, including adding modals, testing, and refactoring. It is a useful tool for improving productivity and saving time, especially for junior developers and those working in unfamiliar domains. Security concerns have been addressed with optional data sharing and different versions for individuals and businesses.

The Talk discusses browser automation using the Worker's Browser Rendering API, which allows tasks like navigating websites, taking screenshots, and creating PDFs. Cloudflare integrated Puppeteer with their workers to automate browser tasks, and their browser rendering API combines remote browser isolation with Puppeteer. Use cases for the API include taking screenshots, generating PDFs, automating web applications, and gathering performance metrics. The Talk also covers extending sessions and performance metrics using Durable Objects. Thank you for attending!