In this presentation, we will delve into the exciting world of creating an AI-powered chatbot using SvelteKit. The session aims to provide an easy-to-digest guide for developers, covering key concepts and tools to seamlessly integrate artificial intelligence into your chatbot project.

Since OpenAI released ChatGPT in late 2022 we've seen a lot of very interesting things pop up in the AI space. Among them are things like Vercel's v0 and openv0. In this talk we'll take a look at how to leverage these tools to build Svelte components.

Asking an LLM about Svelte 5 doesn't get you much useful information, cut-offs in training data mean that when there's a rapidly changing framework the information can be irrelevant.

Just get the LLM to use the internet, init!? Yeah, I'm going to walk through a set of Model Context Protocol tools I use or have built, how I use them in Claude and Cline and (hopefully) do a one-shot prompt to build out a feature straight from the Svelte blog!

What happens when you need to refactor 377 files in a SvelteKit codebase? Without AI, you retire. With Claude Code, you ship it in 11 hours.

This talk walks through real-world examples of using Claude Code for massive refactoring work that would be soul-crushing to do manually. I'll cover:

• How I approach large-scale refactors with Claude (377 files → 364 files → and counting)

• Building and activating Claude Code skills reliably (based on my viral post that's getting 4k+ views in 3 days)

• The workflow patterns that actually work vs the ones that waste your time

• Real examples from production codebases

This isn't about AI replacing developers - it's about using AI to handle the tedious parts so you can focus on the interesting problems.