Designing a Conversational Agent for Client Onboarding & Delegation
Designing a Conversational Agent for Client Onboarding & Delegation
How I designed a multi-turn conversational system that adapts to user intent, sets clear expectations, and responsibly hands off to humans.
How I designed a multi-turn conversational system that adapts to user intent, sets clear expectations, and responsibly hands off to humans.
Context
An award-winning interior design studio relied on manual, phone-based onboarding for every new client inquiry. Senior designers were spending 2–3 hours daily answering repetitive questions about services, pricing, timelines, and process, creating operational bottlenecks, inconsistent intake quality, and delayed project starts.
The business needed a way to scale early client engagement without compromising trust or overloading designers.
My Role
Conversation Designer & Service Designer
I led the end-to-end design of an AI-powered onboarding chatbot, defining the conversation strategy, intent model, escalation logic, and service blueprint to ensure seamless handoff between automated and human touchpoints.
Methods
Designer interviews to understand intake friction and information gaps.
Analysis of 20+ recorded onboarding calls to identify repeated questions and decision points
Client surveys to understand expectations, anxieties, and drop-off moments
Intent modeling (window shopper, inquisitive researcher, goal-oriented client)
Conversation flow design with progressive disclosure and clear exit points
Service blueprint mapping chatbot, CRM, designer workflows, and consultations
Key Insight
The problem wasn’t a lack of information, it was misplaced expertise.
Designers were acting as human FAQs and lead qualifiers. By designing conversations around user intent rather than linear forms, and by clearly defining when AI should inform versus when humans should engage, onboarding could become faster and more respectful of designer expertise.
Outcome
50%+ reduction in designer intake calls within 3 months
10–15 hours/week reclaimed per designer for core design work
85% client satisfaction with the onboarding experience
40% of inquiries resolved via chatbot alone without human escalation
1-week reduction in time from first inquiry to project kickoff
This project reframed the chatbot from a support tool into service infrastructure, demonstrating how conversational AI can scale operations while preserving human-led, trust-based experiences.
Desk Research- Common chatbot failures
Desk Research- Common chatbot failures
Personas based on user intent
Personas based on user intent
Intent Modeling
Intent Modeling
Conversation Flow
Conversation Flow
Service Blueprint
Service Blueprint
Context
Rubenius Interiors, an award-winning interior design studio with global operations, faced friction in client onboarding. Every new prospect needed repeated explanations of services, sectors, and portfolio, and the manual requirements-gathering process slowed down awareness, lead generation, and conversion.
My Role
UX/Product Designer & Conversational Architect
I analyzed common chatbot failures,
Mapped user intent patterns,
Designed personas, and
Built an 8-step conversational framework that adapts to different prospect types while keeping data capture seamless.
Methods
UX Audit: Studied existing chatbots to identify typical drop-off triggers, long threads, unclear pathways, information overload.
User Segmentation: Defined 3 user types aligned with the funnel:
Window-Shopper – browsing for information
Inquisitive Researcher – comparing differentiators
Goal-Oriented Client – ready to share project details
Conversation Architecture: Created a branching flow that intelligently responds to each persona’s intent, from awareness to off-boarding.
Prototyping & Iteration: Built and refined a modular chatbot using free low-code tools.
Key Insight
Clients didn’t follow a linear journey. They entered with different intent levels and forcing them into a single script caused friction. Designing a branching conversation allowed the chatbot to educate, engage, and capture requirements without overwhelming users.
Outcome
The final chatbot delivered a fast, engaging onboarding experience that:
Increased qualified lead retention by 30% in beta
Eliminated repetitive manual explanations
Captured project details upfront (location, scope, budget, preferences)
Supported 24/7 automated lead qualification across all markets
It gave Rubenius a scalable way to understand client needs before the first call, reducing friction and accelerating conversions.