DigitasAI / Client
Redesigning an AI agent creation tool, boosting task success by 40%.
I redesigned DigitasAI’s core “Add Agent” feature into a guided, multi-step flow. By reducing complexity and layering education, I improved task success and reduced support tickets for one of the platform’s most important capabilities.
Role
Product Designer
Timeline
1 Month, Shipped in Jan 2025
Skills
UX/UI Design
User Research
Journey Mapping
Prototyping
User Testing
Dev Handoff
Team
PM / Jessica Tosti
Development / Jair Reina
QA / Alex Fumes
Context
DigitasAI is a generative AI platform that provides safe AI solutions and products for external clients and internal use.
I joined as the second designer on the team and was responsible for creating the design system and redesigning the "Add Agent" feature.
Problem
DigitasAI's core capability, creating custom AI agents, had a low completion rate and a high volume of support tickets.
The original “Add Agent” flow was a single, overwhelming screen filled with technical jargon, unclear steps, and no sense of progress. Users found it daunting and often abandoned it.
Existing Flow: A single, overwhelming screen with unclear steps.
Solution
A guided, multi-step flow that clarifies each stage of agent creation.
Through research, testing, and iteration, I redesigned the experience to improve comprehension and confidence. Key improvements include:
Progress indicators: Visible steps gave users momentum and orientation to complete the task
Inline education: Tooltips and instructional text clarified technical jargon without overwhelming the UI
Progressive disclosure: Surfaced only what was needed at each step to reduce cognitive load
Redesigned flow: A multi-step flow with clear steps and education.
Uploading documents: Previously shown as a plain text field, the action was unclear. The update gives it prominence and clarity, guiding users with confidence.
Success feedback & immediate action: Added confirmation and direct chat option, giving users reassurance and a clear next step with their agent.
Tooltips & instructional text: Added in-line guidance to educate users as they go.
Impact
90%
increase in task success
Measured through usability testing with 5 users on existing vs. redesigned flows.
Reduced
"Add Agent" support tickets
"I've only gotten one ticket this week, and it was someone telling me that this version was much easier to use."
- PM / Jessica Tosti
Approach
Brief
Redesign the Add Agent feature to make AI agent creation more intuitive and successful for non-technical users.
Research
User interviews and surveys uncovered friction with unclear steps, jargon, and a daunting one-screen flow
Stakeholder interviews revealed high support ticket volume tied to agent creation
Secondary research benchmarked comparable agent builders (OpenAI GPTs, Copilot Studio, Dialogflow) and proven patterns for complex flows (progressive disclosure, step indicators, contextual help) to reduce cognitive load
Define
Synthesized user research and stakeholder input into problem and goal statements
Aligned the project on reducing friction in agent creation and improving task success
Journey Mapping
Mapped the end-to-end agent creation flow, identifying where to simplify steps and apply progressive disclosure to reduce cognitive load
User Testing
Ran 5 usability sessions with professionals
Findings: Multi-step flow boosted comprehension; tooltips supported non-technical users; progress indicators motivated task completion
Delivery
Shipped high-fidelity specs
Partnered with engineering for feasibility checks and QA for validation, ensuring smooth implementation
