agentic-engineering-with-svelte.md

title	Agentic Engineering with Svelte
tags	svelte
format	Workshop: 2 days
subtext	Bookable for teams - on-site or remote
description	Learn how to use AI agents effectively in Svelte 5 and SvelteKit projects, from setup and MCP integration to test-driven workflows, code review, automations, and production debugging.
introduction	<p>This hands-on workshop teaches teams how to use AI agents as effective engineering collaborators when building Svelte 5 and SvelteKit applications. Participants learn how to set up a production-ready project, use the Svelte MCP server, skills, subagents, validate generated changes, and combine TDD, code review, repository automations, and observability into a reliable AI-assisted workflow.</p>
hero	color image imageAlt purple /assets/images/workshops/agentic-engineering-with-svelte/hero.jpg Photo of a computer screen showing an IDE with an open Svelte project
og	image /assets/images/workshops/agentic-engineering-with-svelte/og-image.jpg
topics	title text Introduction to Agentic Engineering We'll introduce agentic engineering and the current challenges of using AI effectively with Svelte 5 applications. title text Project setup We'll create a SvelteKit application with a recommended development stack, including TypeScript, ESLint, Prettier, testing, authentication, database integration, and deployment. title text Svelte MCP server We'll explain what MCP is, how it improves AI-generated code, and how to use MCP tools for documentation lookup, code validation, auto-fixing, and playground generation. title text AI coding best practices We'll cover when to use AI, how to manage LLM context efficiently, and how skills, MCP servers, and context optimization fit together. title text Working with AI agents We'll use sub-agents for parallel and isolated tasks, configure agent instructions in <code>AGENTS.md</code>, and discuss security considerations for MCP servers and AI skills. title text AI-assisted UI/UX workflow We'll explore how to convert a design from Figma into code and how to use agents without losing design intent or implementation quality. title text Development workflow We'll establish a Git workflow for reviewing AI-generated changes, practice Test-Driven Development with AI agents, build reusable components following TDD principles, and explain why tests are essential for both engineers and agents. title text Prompting strategies We'll compare a direct prompt with a structured planning approach by solving the same complex task both ways, then analyze when planning produces better outcomes than immediately generating code. title text Kanban board implementation We'll kick off a Kanban board implementation using the established AI-driven workflow, including when to update <code>AGENTS.md</code>, what belongs there, how to create codebase-specific skills, and how to write ad hoc ESLint rules that keep the agent on track. title text Code review with AI We'll explore AI-assisted code review options, set up Greptile, and use it to review and improve generated code. title text Repository automations We'll set up repository automations that automatically triage issues and improve CI workflows. title text Loop engineering We'll direct agents to validate their work in a loop, extending the maximum useful duration of tasks by combining code changes, validation, pull requests, review feedback, fixes, and repetition. title text Observability and debugging We'll integrate Sentry into the application and use it to diagnose, debug, and fix runtime issues in an AI-assisted development workflow.
leads	handle paoloricciuti