Cleveland will demonstrate how he built a working AI chatbot using SvelteKit and Svelte 5 that embodies Mayor Harold Washington's strategic thinking - not just his quotes. This "Ancestral Algorithm" approach shows how to create conversational AI interfaces that preserve cultural knowledge and decision-making frameworks.

Technical highlights:

SvelteKit + Ollama integration for local AI Svelte 5 reactivity for real-time conversational UI Semantic HTML and accessibility considerations Designing culturally-grounded interfaces (Bronzeville living room aesthetic)

Cleveland will show the live demo, walk through key code patterns, and discuss how Svelte developer experience made rapid prototyping possible for culturally-specific AI applications.

Ever wondered how your scribbles on Snapchat turns into a smooth line, or how the pen tool works in Figma or Procreate? In this talk we'll dive into the invisible art of line-drawing algorithms.

We'll start from the historical pixel-based methods to the tools that we use today, wrapping up with real-world examples.

The techniques described are evergreen, timeless and cross-platform.

Emotions consume 80% of our lives, while the other 20% is intellect (Lough, 2006). Yet when it comes to service design, it still feels uncomfortable talking about emotions in particular in government. With this statistic in mind, can we really afford to ignore emotions when designing services?

This talk covers the what, the why, and the how of designing for emotions, sharing tools and techniques to help move conversations from dark art to serious strategy.

In this talk, Kerrie combines theoretical models, real-life case studies, and practical techniques to help participants curate their own toolkit to embed emotions in their agile practice.

Movies have promised the future where we can talk to AI Assistants with natural language and have them respond with all the nuances of humans. However for years we've been stuck with really "stupid" AI experiences over voice. With the advent of LLMS this is finally a reality!

Lots of different technologies have come together to create amazing audio experiences. However, there are some technical problems that we need to solve. In this talk we will learn how to chain these technologies, solve some of the common problems and build a new JARVIS together, powered by the LLM of your choice.