LOADING
In this talk, I’ll guide you through the crossroads where Scala intersects with AI, some applications aimed at boosting developer productivity, others focused on integrating your code with LLMs.
Artificial Intelligence (AI) is a term increasingly applied to a wide range of things every day, becoming a buzzword, especially among skeptical users. AI may refer to chatbots like ChatGPT, command-line coding assistants, IDE features, frameworks for building Model Context Protocol (MCP) servers for connecting tools and language models, or virtually any project involving a Large Language Model (LLM). It can even extend to no-code AI automation platforms like n8n, an open-source tool that lets you connect services and build workflows visually: self-hostable and highly customizable. Does that sound confusing? If so, do not fret, you are not alone!
In this talk, I’ll guide you through the crossroads where Scala intersects with AI, some applications aimed at boosting developer productivity, others focused on integrating your code with LLMs.
By the end of the talk, we’ll build a simple Scala application that can be incorporated into your agentic workflow and used within a no-code AI flow, making it self-hostable.
Key Takeaways:
1. Understand the current AI ecosystem in Scala: tools, frameworks, and interoperability.
2. Learn how to combine no-code platforms (like n8n) with Scala-based tools for real-world AI integrations.
3. See a demo of a custom MCP server written in Scala, and how it augments n8n workflows.
4. Leave inspired that individual developers and small teams can meaningfully innovate in the AI + Scala space.
We'll explore type classes in Scala 3, using its new rules for givens, extension methods, and mechanisms for automatic derivation via mirrors or macros.
In this presentation, I will demonstrate how we leveraged the strengths of Scala and TypeScript to develop a collaborative text editor that meets the strictest standards for security, performance, and real-time collaboration.
Do you like it when compiler generates the boring code for you? Fast, mundane, boring-but-error-prone code? Do you need to implement such a code generator yourself? Have you found out that Shapeless/Mirrors bend your brain a bit too much?
Code generation is one of the most promising applications of large language models (LLMs), offering substantial productivity boosts for developers. However, this benefit is tempered by serious concerns surrounding the correctness and security of the generated code - especially outside the happy path.
This will be a live coding demonstration of Scala's newest feature set: capture checking.
