Abstract

Libraries and frameworks are where LLMs often break down: too much context, too many moving parts, and lots of hidden assumptions. In this talk, we’ll unpack why models struggle in this space and present our method for structuring library knowledge into digestible chunks. Using Svelte as the running example, you’ll see what goes wrong when models get it wrong, and how Tessl's approach can help them finally get it right.

Overview

Why frameworks and libraries trip up LLMs

Software engineering, among other things, requires precision in language, API patterns, and dependency versioning. But models are trained on snapshots of data that:

• Are taken in the past, meaning they have no knowledge of a framework just released;
• Contain mixed and sometimes contradictory information about the same package. For example, different versions without clear differentiation;
• Provide an unbalanced distribution of information. Some packages are well-documented, while others have very little coverage.

We’ll unpack why this matters for developers relying on AI coding tools and introduce a practical tool to help.

Tessl's method

• Structured, doc-like blueprints of a package’s API, best practices, and examples.
• They give coding agents a reliable reference point while iterating, helping them stay aligned with how a library is really meant to be used.

Svelte as a running example

• Svelte poses a particular challenge: LLMs often mix it up with other frameworks or fall back to using older Svelte versions patterns.
• With our method, the same agent can navigate the framework more effectively, producing cleaner, more accurate code.

Design systems are often seen as essential in growing organizations. However, where design team is under-resourced, maintaining and evolving a coherent system becomes a challenge. This talk presents a pragmatic, engineer-led approach to promoting, using concrete React patterns and architecture.

In the fast-paced world of software development, AI tools like Cursor and Qodo are game-changers for building features and boosting productivity. This talk dives into real-life examples of how these tools can fit right into your daily routine, taking care of repetitive tasks, fine-tuning your code, or even building the whole feature for you end to end by an AI agent. By tackling the common struggle of time crunches, these tools help you become a 10x more productive developer. You'll walk away with practical tips and strategies to instantly up your efficiency and teamwork, giving you a fresh take on using AI to tackle everyday coding challenges. Ready to tap into AI's full potential and redefine what it means to be productive in development?

React development often doesn’t mean JUST React anymore. Frameworks like NextJS are on the rise and they offer a lot of power out of the box.
But how does it really work in the background? We’ll explore how different rendering strategies like SSR, SSG, CSR or ISR work, when to use each one, and how NextJS can optimise rendering, enhance page speed, and simplify server-side functionality in your React apps.

Cloudflare has a unique developer platform and is a great option to host your SvelteKit app.
We'll show you how to get started and some of the lessons we've had running it in production.

Every want to build something but was told you shouldn't by "The Internet"? Me Too. Here's the story of how I chose to ignore those people and finally do the thing I've wanted to do since I was a kid, make a video game!

Every want to build something but was told you shouldn't by "The Internet"? Me Too. Here's the story of how I chose to ignore those people and finally do the thing I've wanted to do since I was a kid, make a video game!

Ever want to build something but was told you shouldn't by "The Internet"? Me Too. Here's the story of how I chose to ignore those people and finally do the thing I've wanted to do since I was a kid, make a video game!