AI-Powered Learning Platform
Evolv
Evolv is an AI-powered learner management platform built to help users create personalized learning paths based on job roles and skill requirements. The platform combines structured training programs with AI assistance to simplify curriculum creation and learning management.
As a UI/UX Designer at Revature, my contribution focused on designing two key modules within the platform: RevGPT, an AI-driven system that helps generate tailored learning paths, and Attendance Management, a workflow designed to manage and track multi-session training programs efficiently.
Context
Enterprise learning platforms often require administrators to manage training programs, track participation, and ensure learners follow structured learning paths. Many systems struggle to balance flexibility with clarity, especially when dealing with multiple sessions and AI-generated recommendations.
Evolv was built to address this gap by combining AI-assisted curriculum generation with tools that allow organizations to monitor training participation effectively.
The platform needed to support two major workflows:
• Generating structured learning paths using AI
• Managing attendance and participation across training sessions
Designing interfaces that could handle these workflows without overwhelming users was a key goal of the project.
Project Domain & Timeline
Learner Management System
Oct 2025 - Mar 2026
Tools
UX Design, Design Thinking, User Flows, B2B Design, Software as a Service (SaaS), Wireframing, Prototyping, Web Application Design, UI Design, Figma, Photoshop, Illustrator
Challenge
Problem
Managing enterprise training programs often involves complex processes that require both automation and clarity. Existing workflows within learning management systems frequently require manual effort and make it difficult to track learning progress efficiently.
Some of the key issues identified were:
• Creating personalized learning paths manually required significant time and effort
• AI-generated recommendations needed to remain transparent and editable
• Tracking attendance across multiple sessions created administrative complexity
• Coordinators needed a clear overview of learner participation and progress
These challenges highlighted the need for a more structured and intuitive interface.
Hypothesis
If the platform could combine AI-generated curriculum suggestions with structured workflow interfaces, training coordinators would be able to create learning programs faster while maintaining visibility into learner participation.
The design approach focused on:
• Making AI-generated learning paths easy to review and modify
• Structuring attendance workflows to support multiple sessions
• Presenting complex data through clear dashboards and structured layouts
• Maintaining consistency across the platform through reusable UI components
By simplifying these workflows, the platform could improve both efficiency and usability.
Research
Competitive analysis
To understand how learning platforms currently support training management, I reviewed several existing learning management systems and enterprise training tools.
The analysis revealed that most systems focus heavily on content management but often lack efficient tools for generating structured learning paths or tracking training participation across sessions.
Common observations included:
• Curriculum creation workflows were often manual and time-consuming
• Attendance tracking features were limited to single-session tracking
• Dashboards frequently presented complex data without clear hierarchy
These insights helped guide the design direction for Evolv.
Screenshots of competitor's website for competitive analysis
System story
The system was designed around two primary workflows: generating learning paths and managing training sessions.
RevGPT introduces AI-assisted curriculum creation, allowing users to generate structured learning paths based on role requirements. This helps training coordinators quickly assemble learning programs while still maintaining control over the final structure.
The Attendance Management module supports training programs that span multiple sessions, enabling coordinators to track attendance and monitor participation over time.
Together, these modules help organizations manage learning programs more efficiently.
What?
An AI-powered learner management platform that generates personalized learning paths and tracks training participation.
Who?
Training coordinators who manage learning programs and learners who participate in structured training sessions.
Why?
To reduce the complexity involved in building training programs and monitoring learner engagement.
How?
By combining AI-assisted curriculum generation with structured workflows for attendance tracking and training management.
Personas
The platform primarily supports two types of users.
Training Coordinators
Responsible for organizing training programs and monitoring learner progress.
Needs:
• Efficient tools to create and manage training programs
• Clear dashboards showing participation and progress
• Easy attendance tracking across multiple sessions
Learners
Participates in structured training programs assigned by the organization.
Needs:
• Clear visibility into assigned learning paths
• Easy access to learning materials
• Progress tracking across training sessions
Persona for the tenant and landlord
Working Backwards
Designing Evolv required understanding how users interact with the system and working backwards from their goals.
The design process focused on simplifying complex workflows and ensuring that the interface remained clear even when handling large amounts of training data.
The following steps helped shape the design.
Moodboard
The visual direction focused on clarity and simplicity. The moodboard explored interface references that emphasize clean layouts, structured dashboards, and minimal visual distractions.
Key inspiration points included:
• Clear hierarchy in data-heavy dashboards
• Balanced spacing and layout
• Neutral color palettes with clear status indicators
Sketch on paper / figma design
Early sketches and Figma explorations were used to define the structure of the platform. These initial designs helped determine how information should be organized across dashboards, curriculum generation screens, and attendance tracking views.
Design and user flow sketches on paper
These explorations allowed the team to test layout ideas quickly before moving into detailed interface design.
Task Flow & User Flow
The task flow for the platform was structured around the key actions performed by training coordinators.
Typical tasks included:
• Creating a new training program
• Generating learning paths using RevGPT
• Assigning programs to learners
• Monitoring attendance across sessions
Designing clear task flows ensured users could complete these actions quickly without unnecessary steps.
RevGPT Workflow
• Define job role or learning objective
• Generate curriculum using RevGPT
• Review suggested learning modules
• Customize the generated learning path
• Save and assign the curriculum
Task flow for all the functionalities in draw.io
Attendance Management Workflow
• Create training session
• Add participants
• Mark attendance during each session
• Track attendance across multiple sessions
• Generate attendance reports
User flow for the application in draw.io
Style guide
The visual design of Evolv follows a structured design system that ensures consistency across the platform.
The design emphasizes clarity and readability, especially in dashboard environments that display large volumes of data.
Typography
The platform uses Source Sans 3 as its primary typeface. The font was selected for its clarity and readability across dashboards and detailed interface components.
Its balanced character spacing and clean appearance help maintain legibility even in data-heavy views.
Colors
The color system uses a neutral base palette combined with accent colors that highlight important information such as status indicators, alerts, and interactive elements.
This approach ensures that users can quickly interpret data without visual overload.
Iconography
Icons were designed to remain simple and functional, supporting navigation and improving recognition of common actions throughout the platform.
The icon system helps users quickly identify features such as dashboards, reports, attendance tracking, and curriculum management.
Buttons
Buttons and interactive components were designed with clear hierarchy and consistent states to guide user actions throughout the interface.
Primary actions are visually emphasized, while secondary actions remain accessible without creating visual clutter.
Style guide for the application
Prototype
An interactive prototype was created to demonstrate how the platform functions across its key workflows.
I used Figma to create an interactive Hi-fi prototype, which represents the product closest to the final design in terms of UI components, colors, layouts, and functionalities. Hi-fi prototype allows me to examine usability issues in detail and fix them at an earlier stage.
Low-Fidelity Screens
Low-fidelity wireframes were used to establish layout structure and information hierarchy. These early screens helped define how dashboards, curriculum generators, and attendance views should be organized.
Low/Medium - Fidelity Wireframes
High-Fidelity Screens
High-fidelity designs refined the visual presentation of the platform, introducing typography, color hierarchy, and detailed UI components
Style guide for the application
Prototype
Prototype in Figma for the usability testing
