Nia: A Full-Service GenAI Shopping Agent
Overview
Nia is a GenAI-powered agent that transforms the complex B2B buying journey into a single, seamless conversation. Unlike traditional chatbots that only answer questions, Nia handles the entire shopping process—from technical discovery and side-by-side product comparison to final checkout.
Role
Product Designer
Led the design of a GenAI shopping agent, evolving a fragmented AI vision into a high-impact, integrated workflow assistant. Built the underlying AI framework and steered the cross-functional product strategy.
Keywords
GenAI Agent
End-to-End Commerce
B2B
purchase flow
↑ 15% higher
bundle attachment
↑ 12% boost
in user satisfaction
01 :AI suggests personalized products based on the user profile and allows adding items directly to the cart.
02 : When users click “Add to cart,” the action automatically prompts AI to confirm and display “Add computer to cart.”
03 :AI generates intelligent follow-up questions to naturally guide the user through the next step.
04 :After the item is added, AI provides a real-time cart summary for quick review and continued interaction.
Background
As AI began reshaping digital products, our organization—traditionally focused on enterprise solutions—wanted to explore how artificial intelligence could meaningfully enhance customer experiences. However, the initial goal was vague: “Let’s add AI to the platform.”
Goal
🎯 1. Establish a scalable AI framework
Create a structured, human-centered approach that clarifies AI’s role and can be adopted across teams.
✨ 2. Enhance user experience through AI
Design intelligent, transparent features that simplify decisions and personalize the shopping flow.
🧭 3. Explore AI’s strategic value
Turn abstract ambition into actionable insight, shaping ethical, long-term AI integration within the product ecosystem.
Challenge
🤖 1. Lack of AI Clarity
The organization wanted to integrate AI but struggled to define its real purpose, scope, and business impact.
🌀 2. “AI as a Buzzword” Mindset
AI was often treated as a trend rather than a strategic tool, leading to misaligned goals and unclear priorities.
🔍 3. No Shared Framework
Without a unified approach, teams explored AI in silos—resulting in fragmented experiments instead of cohesive, user-centered solutions.
Final delivery (short term)
01 :Users can access the AI assistant by clicking the “Nia” tab located in the top navigation bar.
01 :The assistant automatically summarizes the added items in natural language for quick confirmation.
02 : AI prompts customers to add protection plans or accessories, allowing them to complete the entire checkout process directly within the chat.
03 :A live cart summary updates in real time, giving users the option to review, adjust, or proceed to manual checkout at any point.
Final delivery (long term)
01 :Embed Nia into the search flow to help users refine and navigate results efficiently. The assistant provides conversational filtering, personalized suggestions, and intent-based follow-up questions to streamline product discovery.
01 :Replace long feature lists with a real-time AI assistant. Nia answers specific user questions about product differences and suitability directly on the PDP, accelerating the decision-making process.
Design Procoss
Phase 1: Empathize & Align
AI Tools: Microsoft Azure OpenAI Service, Google Cloud Natural Language API, Google Gemini
How we find the problem
We fed NPS survey results from Power BI into Azure OpenAI Service and Gen AI tools to analyze 500+ user feedback and capture the most common complaints and pain points.
Collaborative Validation Through Lean Product Canvas
📊 Lean Product Mapping Synthesized AI-generated pain points to align user challenges with business value.
🤝 Team Validation Partnered with product and engineering to stress-test assumptions and refine problem statements.
🎯 Strategic Alignment Prioritized high-impact opportunities and core user needs to focus the design phase.
Persona Development
Identifying the "Confidence Gap" Through AI-assisted analysis and workshop, we discovered that the primary barrier to purchase wasn't a lack of options, but a lack of technical confidence. For users like Rob, decision fatigue stems from the high stakes of enterprise procurement. My goal was to pivot Nia from a "search tool" to a "decision support system" that bridges this technical gap.
1. Overwhelmed by Product Comparisont issues
“There are just too many options. Every brand says theirs is the best, but I can’t tell what really fits our team’s needs.” – Business Operations Manager (Male, 40s)
2. Reliance on Price & Brand Reputation
“I usually just go with the same brand we’ve used before or whatever’s on sale — I don’t really know the technical differences.” – Procurement Specialist (Male, 38)
3. Time-Consuming Procurement Workflow
“It takes me hours to gather specs and check compatibility. I wish there was a quicker way to know what actually works together.” – Procurement commdoities (Female, 45)
Phase 2: Explore
AI Tools: Google Gemini
Unlocking AI-Driven Insights,At this stage, we focus on how Nia can enhance the user experience by providing relevant, actionable information. This involves two key steps:
1 : Define Opportunities
🧠 AI-Powered Guidance
🎯 Personalized Recommendation Engine
💬 Context-Aware Interactions
🔎 Explainable AI Design
🛒 Seamless End-to-End Flow
2 : Data Strategy & Engineering Sync
Partnered with data and engineering teams to build a robust technical foundation for Nia:
✅ Sourced: Aggregated specs, pricing, and user data.
✅ Structured: Defined data logic for accurate AI responses.
✅ Scaled: Built a flexible integration for future AI expansion.
Phase 3: Design
AI Tools: Figma make, Miro, Stitch
User Testing: Validation
We quickly put this MVP into usability testing to validate how customers would use AI during real shopping scenarios.
Feedback
❌ Interrupted shopping flow
Users had to leave product pages to interact with the AI, breaking their browsing momentum.
❌ Lack of side-by-side comparison
Customers couldn’t compare products while chatting with Nia at the same time.
Team Recommendation
✔️ Persistent sidebar assistant
Keep Nia accessible while users continue browsing and comparing products.
✔️ Conversation continuity
Allow users to navigate freely across pages without losing their AI interaction.
Persistent Sidebar (Launched)
To maintain shopping momentum, we pivoted to a persistent sidebar
Key Advantages:
🛍️ In-Context: Browse and chat simultaneously without leaving the page.
🔄 Continuous: Chat history persists across the entire shopping journey.
⚡ Efficient: Real-time comparisons accelerate decision-making.
⏳ Lean: Optimized for a fast, high-impact MVP launch.
Deep Page Integration (Future)
🔍 Search Results: Ask Nia to filter, compare, and clarify specs in real-time.
📄 Product Pages (PDP): Get instant answers on compatibility and upgrades at the moment of decision.
Impact: Reduces friction by providing a smoother, more personalized experience without ever leaving the page.
purchase flow
↑ 15% higher
bundle attachment
↑ 12% boost
in user satisfaction
This project accelerated the team’s AI maturity—giving us a shared framework, a clearer understanding of AI’s role, and a concrete path for future adoption. For a traditionally structured enterprise, this was a major step toward scalable AI integration.
The MVP didn’t just deliver new functionality—it helped the organization confidently move toward an AI-driven future.