Case Study · UX Discovery & Agentic AI
Publicis Sapient · ABC Supply Co. · B2B Roofing, US · Mar–May 2026

From 53 AI opportunities to a working Agentic prototype in a 2-week sprint.

Led UX discovery and experience exploration for a leading B2B roofing supply enterprise — auditing an existing ecommerce ecosystem, mapping the Agentic AI opportunity space, and shipping an end-to-end prototype that embedded intelligent workflow assistance directly into the customer dashboard.

UX Discovery Agentic AI UX Strategy Competitive Research Interaction Design B2B Ecommerce
ABC Supply customer dashboard showing the AI-driven 'Today's Priority Actions' panel surfacing at-risk accounts, expiring quotes and high-value returns

Final direction — a persistent, docked "Today's Priority Actions" panel embedded in the dashboard.

ClientABC Supply Co. · B2B Roofing Distribution
RoleExperience Design Lead
Timeline3-month engagement · Mar–May 2026
PlatformsResponsive Desktop · Tablet · Mobile

A mature B2B ecommerce ecosystem, ready for its next layer.

ABC Supply's digital storefront already served customers, associates and vendors across desktop, tablet and mobile. The engagement had two parallel tracks: scalable UX enhancements to the existing ecommerce experience — improving usability, workflow clarity and enterprise user efficiency — and a forward-looking exploration of where Agentic AI could meaningfully change how contractors, branch associates and vendors get work done.

Over three months I worked cross-functionally with Product Owners, an Associate Director of Product Management, and North America-based Design Leadership to move from broad opportunity mapping to a validated, working prototype.

Product Owners
Prioritized use cases against roadmap and platform constraints.
Associate Director, Product Management
Aligned discovery output to enterprise strategy and stakeholder expectations.
NA Design Leadership
Reviewed direction and quality bar throughout the sprint cadence.
Design Thinking UX Strategy Interaction Design Competitive Research AI Experience Exploration Stakeholder Workshops Rapid Prototyping

Where B2B AI actually lives today — and where it doesn't.

Before proposing anything new, I benchmarked how AI shows up across six B2B and adjacent platforms — Grainger, Wayfair, Ferguson Enterprises, MSC Industrial Direct, Salesforce Agentforce and ServiceNow Now Assist — scored across five dimensions: category, placement, persona, contextual awareness and proactivity.

Comparative summary table scoring Grainger, Wayfair, Ferguson Enterprises, MSC Industrial Direct, Salesforce Agentforce and ServiceNow Now Assist across category, placement, persona, contextual awareness and proactivity
Competitive teardown of Grainger's embedded search and backend AI capabilities
Grainger — the category leader by scale, but AI is invisible infrastructure: no named persona, and personalization limited to inventory-management tools rather than the storefront itself.
Competitive teardown of Ferguson Enterprises' PRO Plus platform AI capabilities
Ferguson Enterprises — the closest B2B supply analog. Proactive seasonal-demand alerts were tied to a confirmed 10% increase in contractor satisfaction, reinforcing "proactive over reactive" as the strongest pattern to borrow.
Competitive teardown of MSC Industrial Direct's AI-driven personalization capabilities
MSC Industrial Direct — content recommendations work, but storefront alerts and named personas remain absent, mirroring the wider category gap.
Competitive teardown of ServiceNow Now Assist / AIx enterprise AI agents
ServiceNow Now Assist / AIx — role-aware, named agents embedded in every corner of the platform, offered as an architectural reference rather than a direct competitor.

The synthesis surfaced a clear white space: no direct B2B construction-supply competitor had shipped a named, customer-facing AI persona, and none activated AI meaningfully at the product-detail level — despite Wayfair reporting a 33% lift in add-to-cart when AI-driven recommendations appeared there. Those findings, plus the "floating icon vs. inline touchpoint" placement question, became the design brief for ABC Supply.

Design implications document for ABCsupply.com covering named AI persona, product-detail-page contextual surfacing, proactive-over-reactive patterns, placement decisions, and B2B-specific AI value

53 possibilities, narrowed to 5 that mattered.

Working alongside Product and Design Leadership, I helped define and prioritize 53 potential AI/Agentic experience opportunities spanning the full ABC Supply ecosystem, then stack-ranked them against customer, associate and vendor pain points to arrive at 5 high-impact, enterprise-ready use cases.

53
Opportunity areas identified
→
5
High-impact use cases prioritized
→
3
Carried into the prototype sprint
1
Real-Time Intelligent Quote Requesting — surfacing product, pricing and availability context the moment a quote is started.Prototyped
2
Review Order Approval with Anomalies — flagging pricing or quantity anomalies before an order is approved.Prototyped
3
AI-Generated Alerts for Proactive Notifications — weather, job-site and account signals turned into timely, actionable alerts.Prototyped
4
Vendor & Branch Operational Assistance — workflow support for associates managing deliveries, returns and account health.
5
Project-Based Recommendations — AI that understands the job, not just the SKU, and recommends a complete materials list.

An end-to-end Agentic AI prototype, built in 2 weeks.

With direction validated, I conceptualized and delivered a working prototype within an accelerated 2-week sprint — integrating intelligent workflow assistance directly into the dashboard rather than isolating it in a separate chat experience. Each use case below was built as a full, click-through flow and reviewed in fast-paced stakeholder workshops.

01
Real-Time Intelligent Quote Requesting
Contextual product & pricing guidance from the first click.

The flow surfaces job-site photos, product matches and pricing context inline as a quote is built — replacing manual lookups with assistance embedded directly in the task.

Prototype Flow — UC1
Filmstrip of the Real-Time Intelligent Quote Requesting prototype flow, showing job-site photo capture, product matching and quote screens
02
Review Order Approval with Anomalies
Catching pricing and quantity anomalies before approval.

An assistant panel walks the approver through flagged line items conversationally, explaining why an anomaly was raised and what action resolves it — keeping approval fast without losing scrutiny.

Prototype Flow — UC2
Filmstrip of the Review Order Approval with Anomalies prototype flow, showing the AI assistant flagging order anomalies for approval
03
AI-Generated Alerts for Proactive Notifications
Turning job-site and account signals into timely alerts.

Rather than waiting for a customer to ask, the system pushes proactive, contextual alerts — echoing the "proactive over reactive" pattern validated in the Ferguson research — directly into the associate's daily workflow.

Prototype Flow — UC3
Filmstrip of the AI-Generated Alerts for Proactive Notifications prototype flow

Surfacing AI without disrupting the work underneath.

The research raised a specific placement question: a floating, persistent panel reads as high-visibility but can feel intrusive during casual browsing, while an inline or modal touchpoint is lower-friction but easier to miss. I prototyped both directions for the "Today's Priority Actions" surface and tested them against ABC Supply's actual working screens.

Overlay — Modal
Overlay exploration: 'Today's priority actions' presented as a centered modal over the dashboard
Docked Panel — Persistent Selected direction
Side panel exploration: 'Today's priority actions' docked persistently beside recent orders

The docked panel won out — it kept priority actions constantly visible for the power users (branch associates, account managers) who rely on it most, without blocking the order table underneath. I also explored the resolved/completed state so the panel reads as a living to-do list rather than a static alert feed.

Action Needed
Overlay state showing an unresolved high-risk account alert
Resolved State
Overlay state showing a completed action with success styling after the associate takes action
06 — Outcomes

A validated direction, delivered at pace.

The engagement moved from open-ended discovery to a client-reviewed, working prototype in three months — with the AI concept itself proven end-to-end in two weeks.

53 → 5
Opportunities Prioritized
Down to 5 enterprise-ready use cases
2 Weeks
Prototype Sprint
Concept to end-to-end clickable flow
3
Platforms Supported
Desktop, tablet & mobile layouts
Client-Reviewed
Strong Stakeholder Reception
Recognized for execution quality and turnaround speed
Back