From cramped chaos to clarity
Evolving Dell’s AI Support into a Purpose-Built Workspace, which cut ticket volume by 55% and boosted self-serve adoption to 92%
Dell employees faced fragmented tools and slow resolutions due to a cramped chat interface. IntelliAssist 2.0 replaced this with a full-screen AI platform unifying 12+ APIs and a centralized sales portal, streamlining support and empowering self-serve efficiency
Project snapshot
Problem
Sales teams struggle to efficiently assist customers today because they rely on a cramped, outdated chat interface and must toggle between multiple systems to access essential sales tools and information.
They needed to toggle between multiple systems to find resources like order status, sales guides, or troubleshooting tools while assisting customers.
This fragmented workflow slowed response times, frustrated employees, and delayed critical sales processes. The goal was to unify these tools into a single, modern interface to streamline support and improve efficiency
1
Incomplete Answer Context
The AI’s responses provided only surface-level details without critical supporting information like relevant information, or follow-up questions
Buried Features & Low Adoption
The sparse landing screen failed to highlight the AI’s full capabilities, resulting in low feature adoption as employees defaulted to peer-dependent learning
2
Business-Driven Scalability & Unified Experience Demands
The business required a stable, future-proof platform to integrate new functionalities (e.g., AI-driven sales analytics) and unify the sales portal’s tools; without integration, employees faced disjointed processes, risking errors and delaying enterprise-wide adoption of AI tools
What Users Were Saying?
“I just use bookmarks. Searching takes too long.”
“The chatbot gives generic answers — I can’t trust it.”
“I have to ping a teammate to get the right resource.”
Through user interviews, a clear pattern emerged: employees lacked confidence in the tool, found it slow to navigate, and rarely discovered features on their own.
This led to low adoption, fragmented workflows, and delays in customer resolution.
What I Set Out to Solve
I reframed the challenge around three key principles
Speed: Help users get to the correct answer faster
Clarity: Provide context-rich, human-readable responses
Trust: Build confidence through transparency and personalization
Each design decision — from role-specific prompts to source-tagged answers — was designed to shift behavior, boost adoption, and reduce support dependency.
Solution
Unified Interface for Seamless Workflows
Transitioned from a cramped chat window to a full-screen AI platform with prioritized prompt suggestions (e.g., “Check order status”) and integrated self-serve tiles (e.g., Order Tracking Hub, ERG) directly below the chat
Unified AI and self-serve tools into a single workspace, directly tackling fragmented workflows and cutting resolution times
1
Smart Search Prompt
Affordance · Contextual Onboarding · Behavior Design
Why: User testing revealed hesitation around what to ask. I introduced role-specific prompts to reduce friction, guide first-time use, and highlight AI capabilities.
These soft nudges boost perceived relevance and support progressive discovery—all without overwhelming the interface.
2
Familiar Cards from Legacy Design
Change Management · Perceived Control · Mental model
Why: To ease adoption, I retained the familiar card layout from the legacy interface. This preserved mental model continuity, reduced cognitive friction, and helped users feel more in control of the new system.
This small but intentional decision improved learnability and supported a smoother behavioral transition to the AI-powered workflow.
🚨 Phased Transition Strategy
Self-serve tiles were prioritized at launch to ease adoption, with plans to phase them out as AI usage grows—balancing familiarity with long-term efficiency.
Full-Screen Interface for Contextual Efficiency
Transitioned to a full-screen interface to unify AI chat, self-serve tools, and contextual resources in one workspace—eliminating system juggling and retaining user focus through dynamic panel controls
Centralizing tools and AI simplifies workflows, cuts redundant tasks, and reduces reliance on multiple systems—lowering operational costs and supporting scalable growth
3
Sources & Related Articles
Transparency · AI Explainability · Trust Design
Why: I added visible sources and related links to increase the credibility of AI responses and help users feel more confident in what they were seeing.
This supports AI explainability, gives users a way to independently validate results, and builds trust without dependence — especially important during early AI adoption.
2
Follow-up / “Search Instead” Prompts
Intent Refinement · Conversational UX · Cognitive Support
Why: These prompts serve as contextual suggestions, helping users reframe their queries or explore related topics when AI responses fall short.
They reduce blank states and reinforce conversational UX patterns, making the AI experience feel more responsive and guided.
1
Collapsible Resource Sidebar
User Control · Flexibility · Fallback UX
Why: To give users a sense of control, I added a collapsible sidebar so they could self-navigate if the AI response fell short.
This acted as an escape hatch, offering a familiar fallback path that boosted confidence and supported smoother adoption during the transition to AI-assisted workflows.
🚀
Workflow Streamlining
Centralizing AI chat, self-serve tiles, and sales tools cut redundant tasks (e.g., order tracking) by 40%, letting employees focus on high-value work
✂️
Cut out unnecessary steps
Integrated sales portal resources eliminated daily platform-switching for 72% of pilot users, giving employees more time for high-impact tasks that drive outcomes
💡
Boosted AI Adoption
Tools are now easier to find and use, increased feature discovery by 55%, with 85% of users reporting “easier access to critical tools
What did I learn?
⚖️
Balancing Business Needs ≠ Compromising UX
Strict requirements from leadership often mirrored hidden user needs—like faster workflows—teaching me to reframe constraints as guardrails, not roadblocks
⏳
Limited Time? Prioritized Ruthlessly
With tight deadlines, I learned to prototype only critical flows first (e.g., order tracking), then iterate post-launch—proving agility can coexist with quality
🤝
