Understanding the opportunity

The initial challenge was to make a broad and evolving body of AI knowledge approachable for employees with different levels of experience. Users needed a clear starting point, practical guidance, searchable reference material, and a path to continue learning as their skills developed.

The experience also needed to help standardize design without requiring every user to be a visual-design expert.

The UX Challenge:

How do we help employees move from curiosity about AI to confident, responsible, and regular AI use in day-to-day work?

This framing influenced every part of the experience: the navigation model, learning levels, content hierarchy, visual design, terminology, and progression from basic concepts to professional-level use.

Discovery considerations

The research and discovery work focused on understanding what employees would need to learn, how they would look for information, and what might prevent them from engaging with AI resources.

Key considerations included:

• Different levels of AI familiarity, from first-time learners to advanced practitioners.
• The need to distinguish foundational education from practical tools and advanced workflows.
• The importance of responsible AI, safe data handling, and clear guidance.
• The need for both guided exploration and fast lookup—for example, finding a glossary term, prompt resource, template, or article.
• The value of community and peer learning in making AI adoption feel accessible and ongoing.

These considerations led to a product experience that supports both structured progression and self-directed discovery.

Experience strategy

The strategy was to organize the app around a learning journey rather than a flat list of links. The experience supports progression through Beginner, Intermediate, Pro, and “AI Champion” levels, allowing users to identify an appropriate entry point and understand what to explore next.

The strategy was guided by five principles:

1. Progressive learning: Start with fundamentals and build toward automation and advanced practices.
2. Action-oriented education: Connect concepts to prompts, templates, videos, presentations, quizzes, and real examples.
3. Responsible adoption: Make safe data handling and responsible AI part of the core experience.
4. Findability: Support both browsing by topic and searching for a specific term or resource.
5. Community enablement: Connect learning resources with an AI enthusiast community and opportunities for continued engagement.

This strategy turned a large content set into a coherent product with a clear purpose and a logical path through the material.

Information architecture and content structure

A significant part of the UX work was deciding how to group and label the content. The final structure brings together learning paths, foundational guidance, prompt engineering, terminology, automation education, and community resources.

The primary experience areas include:

• Learning paths: Beginner, Intermediate, Pro, and “AI Champion”.
• AI fundamentals and guidance: Getting Started, AI Foundations, Microsoft Copilot, Responsible AI, Templates, Agents, and related resources.
• Prompt engineering: Prompt Engineering, “What’s Your Prompt?” (prompt sharing feature), Prompt Resources, Prompt vs. Context, Context Resources, and social initiatives (voting, Teams sharing for groups and individuals, and email sharing).
• Reference and discovery: AI Terms, an alphabetical glossary, searchable definitions, articles, resource listings, and accompanying social initiatives (term/resource voting, Teams sharing for groups and individuals, and email sharing).
• Automation education: Power Automate, n8n, multi-tool workflows, and more advanced development topics.
• Community: A place for employees to connect with other AI enthusiasts and continue learning beyond individual lessons. In addition, most sections include ways to add information to ensure a strong and vibrant AI reference tool.

The information architecture was designed to reduce cognitive load: users can enter through a learning level, a topic, a search need, or a practical resource and still find a logical next step.

UX/UI design and visual system

The UI design translated the strategy into a consistent, approachable, and content-rich interface. The screen designs use clear groupings, cards, headings, labels, search, filters, and visual cues to help users understand where they are and what they can do next.

The design work included:

• Establishing the homepage as an orientation point for the experience.
• Creating visual entry points for learning paths and major resource categories.
• Designing layouts for dense educational content without making the experience feel overwhelming.
• Supporting quick scanning through cards, categories, labels, and concise descriptions.
• Designing searchable and browsable glossary and article experiences.
• Using consistent patterns across videos, presentations, quizzes, links, and reference content.
• Aligning the visual language with Cox branding while giving the AI Super Enthusiasts experience its own identity.
• Considering accessibility, readability, hierarchy, responsive behavior, and reusable UI patterns.

The design intent was to make the app feel energetic and modern while preserving clarity and trust—especially important for an internal experience that introduces employees to new and sometimes complex technology.

Copywriting and content design

Copywriting was an important part of the UX because the product depends on helping users understand unfamiliar concepts quickly. Labels and descriptions needed to be approachable for beginners while remaining useful to more experienced users.

The content-design work included:

• Naming and organizing navigation categories.
• Writing concise descriptions for resources and learning areas.
• Making technical topics easier to understand through plain-language explanations.
• Creating a progression from prompting and fundamentals to automation and advanced workflows.
• Defining terminology consistently across the app.
• Supporting discovery with searchable labels, glossary terms, article titles, and calls to action.
• Reinforcing responsible AI and safe data practices through the learning journey.

The result is a content model that treats language as part of the interface—not simply supporting text added after the UI was designed.

Development and design-to-build collaboration

The development phase required translating the UX strategy and UI patterns into a working Power App. The focus was on preserving the intended information architecture, reusable visual patterns, content relationships, search and filtering behavior, and learning progression during implementation.

The design-to-build process included:

• Communicating page structures, interaction expectations, and content relationships.
• Supporting implementation decisions within Power Apps and the available Cox environment.
• Reviewing working screens and identifying gaps between the intended design and the implementation.
• Refining layouts, labels, content density, and navigation based on build realities.
• Balancing ideal experience design with maintainability, scalability, and the ability to add future AI resources.