Finding regulations or laws is tough, especially for non-experts. How can they even start and be sure they’ve got the right, accurate info? Even legal pros struggle sometimes 😕. Euro Law (formerly Eur-Lex) is a new search tool for the EU Parliament’s regulations and laws, which is the EU’s lawmaking body. It’s for everyone from politicians to regular folks needing specific legal information in their huge library.
To redesign navigation and search functionalities, incorporating new design patterns and AI enhancements, to accelerate information retrieval for both internal teams and external users.
This project was the final assessment for the course Design Patter for Ai Interfaces by Vitale Friedman.
My role as the rest of the team of students was researching about the current problem and design the solution and UX experience using the correct Ai patterns for the interfaces.
This project aims to enhance information accessibility across multiple websites by improving the search functionality. By doing so, we want to help both internal and external stakeholders find information more quickly
We want to
We worked with members of the European Parliament to work on task analysis using analytic tools. This identified the primary tasks performed by both internal and external users on the website. The analysis also assessed the platform’s effectiveness in guiding users to relevant content and documents.
Our team was given access to the European Parliament’s analytics and feedback from the site.
Analysis showed that the overwhelming majority of website traffic comes from search engines, split evenly between mobile (52%) and desktop. Users primarily seek news, facts, or reference materials. This confirms information consumption, not engagement.
As you can see it is a varied mix of content.
The team conducted an event storming workshop to map the entire user journey for the search flow. This collaborative and visual approach, using a Miro board and sticky notes, resulted in a comprehensive blueprint that informed our wireframing process and encouraged creative problem-solving.
Even though temperature and top_p are often seen as engineering details, designers need to understand them. These parameters significantly impact how AI behaves and are essential for creating user-friendly AI experiences that meet expectations.
Temperature is the measure of entropy or chaos in generated output. It is a setting that controls randomness when picking words during text creation. Low values of temperature make the text more predictable and consistent, while high values let more freedom and creativity into the mix, but can also make things less consistent.
Top_p or nucleus sampling is a setting that decides how many possible words to consider. A high top_p value means the model looks at more possible words, even the less likely ones, which makes the generated text more diverse.
For our purposes we chose a low temperature + low top_p. We want simple predictable results that are targeted at a wide range of users.
AI has changed how we interact with technology. While fundamental design principles remain true, the evolution of AI interfaces demand a new approach to user interaction. Here is a selection of patterns I used.
I started on a journey of exploration to refine the search interface’s user experience. Then experimented with different layouts, information architecture, and interaction patterns to optimise the search flow.
Wayfinders
Templates:
Multiple tokens and parameters are needed to form a strong initial prompt: Focus --> Collections, Doc type, topic, date, language, more filters
Filters: Focus
Parameters: Personas
Citations
References: To sources found
Footprints
Summary
Nudges: Chat with source, summarise and compare buttons
Open input: For follow up questions
Citations
References: To sources found
Footprints
Summary
Nudges: Chat with source, summarise and compare buttons
Open input: For follow up questions
