December, 2009

article thumbnail

Sketchy Wireframes

Boxes and Arrows

Introduction When it comes to user interface documentation, wireframes have long been the tool of choice. However, using traditional diagramming tools like Visio, OmniGraffle, and InDesign, most wireframes today look the same as their ancestors did from a decade ago – assembled with rigid, computer-drawn boxes, lines and text. While these artifacts have served us well, they can also be slow to produce, burdened with unnecessary detail and give a false impression of “completion.&#.

article thumbnail

5 Steps to Building Social Experiences

Boxes and Arrows

Nowadays everyone wants social in their sites and applications. It’s become a basic requirement in consumer web software and is slowly infiltrating the enterprise as well. So what’s a designer to do when confronted with the requirements to “add social&# ? Designing social interfaces is more than just slapping on Twitter-like or Facebook-like features onto your site.

Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Tree Testing

Boxes and Arrows

A big part of information architecture is organisation – creating the structure of a site. For most sites – particularly large ones – this means creating a hierarchical “tree&# of topics. But to date, the IA community hasn’t found an effective, simple technique (or tool) to test site structures. The most common method used—closed card sorting—is neither widespread nor particularly suited to this task.

Data 81
article thumbnail

Research Logistics

Boxes and Arrows

With more companies today putting a stronger emphasis on gaining a deeper understanding of their customer, it’s not unusual for us to be called in for a project to find that our clients don’t have a lot of experience with research and don’t know what to expect. This article is for every designer, architect, manager, engineer, and stakeholder who wants to know more about research and is intended to provide you with the most critical tools for interacting with researchers and und

Report 67
article thumbnail

Peak Performance: Continuous Testing & Evaluation of LLM-Based Applications

Speaker: Aarushi Kansal, AI Leader & Author and Tony Karrer, Founder & CTO at Aggregage

Software leaders who are building applications based on Large Language Models (LLMs) often find it a challenge to achieve reliability. It’s no surprise given the non-deterministic nature of LLMs. To effectively create reliable LLM-based (often with RAG) applications, extensive testing and evaluation processes are crucial. This often ends up involving meticulous adjustments to prompts.