Agenda

 You can’t mock with us!

Driving discovery with AI-generated prototypes.

Speakers: Aida Malkić & Martina Margitić 

About: Mockups are more than just pretty pictures. They’re a way to discover what works, test ideas quickly, and spark the right conversations with teams and clients. In this session, we’ll demonstrate how AI can transform rough ideas into clickable prototypes in minutes, help uncover hidden assumptions, and accelerate discovery, making it faster and more enjoyable. You’ll see where AI really helps, where it falls short, and how to use it to learn and adapt without wasting time.

Generating synthetic test data for 

your RAG pipeline: DeepEval vs. Ragas

Speaker: Darko Špoljarić 

About:  The manual generation of training and test data for AI-powered systems is a time-consuming and tedious task. There are various concerns to address, including labeling, completeness, filtering, bias, and quantity. However, when implementing a RAG system, there's already a dataset considered to be of "golden" quality. It's used to generate a RAG context from, so why not use that corpus to create the test data from? Come and learn more about the approach and how the two most popular frameworks today compare in that particular area.

AI and Roleplay. 

Creating Personas with LLMs

Speaker: Alma Trtovac

About: We’ll examine whether—and to what extent—large language models can contribute to shaping (proto)personas for digital product design. Along the way, we’ll also tackle the less glamorous but equally crucial questions: how both LLMs and designers bring their biases to the table, and how we might peek under the hood to see where exactly the model is pulling its wisdom (or nonsense) from.

 Declarative Self-improving Python 

(DSPy)

Speaker: Marco Hrlić

About: DSPy addresses the challenge of constructing compound AI systems by employing a declarative approach, as opposed to 'fuzzy' programming through natural language prompts. Interactions with LLMs, including instructions, context, data structures, and other aspects, are explicitly defined in the code. We'll cover the core principles and design philosophy of the framework by designing and building a simple system to solve a common RAG task. We will conclude with an overview and a demonstration of the optimization techniques offered by DSPy.