CASE STUDY · MORGAN STANLEY

AI Teammate

A voice-first client assistant and advisor configuration portal for service, testing, publishing, and escalation.

Voice UXAI AssistantConfiguration Portal

ROLE

Principal UX Designer

PLATFORM

Mobile · Tablet · Desktop Portal

FOCUS

Voice UX · AI Configuration

TOOLS

Figma · Audio Prototyping · Research

CONFIDENTIALITY NOTE

Some details, screens, and workflows are recreated or generalized to protect confidential information while preserving the design challenge, process, and decision-making approach.

SITUATION

Business context

Advisors needed a hands-free way to access client information and set reminders while on the move or in meetings.

User context

Financial advisors in client-facing scenarios couldn't pause to type — they needed voice-first access to portfolio data, notes, and scheduling.

System context

Existing advisor tools were screen-dependent, creating friction in mobile and meeting contexts where hands-free interaction is essential.

DESIGN CHALLENGE

Design a voice-first experience that is professional, secure, and seamlessly integrated with the advisor's desktop portal.

Screen dependency

Advisors couldn't access critical client data during meetings without visibly checking their devices.

Security concerns

Voice interactions in financial services must handle sensitive data with appropriate privacy controls.

Configuration complexity

Different advisors have different needs — the AI must be configurable without requiring technical expertise.

Voice privacy controlsMulti-modal syncAdvisor personalizationEnterprise security

MY ROLE

What I led

Voice interaction design and the configuration dashboard for the AI's personality, logic, and escalation behavior.

What I designed

Voice conversation flows, visual feedback system, configuration portal, and the testing/publishing pipeline.

Who I partnered with

NLP engineers, voice interaction researchers, compliance teams, and advisor focus groups.

MAKING THE WORKFLOW VISIBLE

Prototyped conversation flows using high-fidelity audio mockups to test intent recognition, response tone, and the boundary between voice automation and human escalation.

VOICE INTERACTION FLOW · INTENT → RESPONSE → ACTION → ESCALATION

EXPLORING THE EXPERIENCE

Conversation Flow Mapping

Designed the branching logic for voice intents, confirmations, and error recovery.

Visual Feedback System

Created the "pulse" and feedback states to indicate listening, processing, and responding.

Privacy Controls

Explored push-to-talk, wake-word, and environment-aware activation models.

Configuration Portal

Designed the advisor-facing dashboard for customizing AI behavior and responses.

Testing Pipeline

Built the flow for advisors to test, iterate, and publish their AI configurations.

Escalation Patterns

Defined when and how the AI should hand off to a human specialist.

THE SOLUTION

A multi-modal system where voice commands on mobile sync instantly with the advisor's desktop workstation, backed by a configuration portal for personalization and control.

PRIMARY SOLUTION · DASHBOARD VIEW

Voice Interface

Natural language interaction with visual pulse feedback and confidence indicators.

Configuration Dashboard

Advisor-facing portal for customizing AI personality, data access, and behavior.

Testing Environment

Safe sandbox for advisors to test voice interactions before publishing.

Multi-Modal Sync

Real-time synchronization between voice commands and desktop workstation.

Escalation Manager

Rules engine for defining when the AI hands off to human support.

Analytics View

Usage patterns, success rates, and advisor feedback dashboards.

KEY DESIGN DECISIONS

Push-to-talk + wake-word hybrid

WHYFinancial environments require explicit control over when the AI is listening.

TRADEOFFSlightly more friction vs. strong privacy guarantees in sensitive settings.

RESULTAdvisors felt confident using the AI in client meetings without privacy concerns.

Visual pulse feedback

WHYUsers need clear indication of AI state — listening, processing, or ready.

TRADEOFFScreen real estate for visual feedback vs. purely audio-only interaction.

RESULTReduced user uncertainty about whether the AI understood their request.

Advisor-controlled configuration

WHYAdvisors know their practice best — they should control how the AI behaves.

TRADEOFFConfiguration complexity vs. AI relevance and advisor trust.

RESULTHigher adoption because advisors felt ownership over the AI's behavior.

Staged publishing pipeline

WHYChanges to AI behavior should be testable before going live with clients.

TRADEOFFSlower iteration cycle vs. reduced risk of embarrassing AI errors.

RESULTAdvisors tested confidently and published with fewer post-launch issues.

IMPACT

USER IMPACT

Advisors gained hands-free access to client data during meetings, improving their responsiveness and professionalism.

BUSINESS IMPACT

Improved advisor meeting productivity by enabling real-time information retrieval without screen dependency.

OPERATIONAL IMPACT

Reduced the friction of note-taking and action item capture during client conversations.

PRODUCT IMPACT

Established the voice UX framework and configuration portal pattern for future AI assistant products.

REFLECTION

What I learned

Voice in fintech isn't just about convenience; it's about making high-stakes information accessible at the speed of thought.

What I would improve

I would invest more in contextual awareness — the AI should adapt its behavior based on whether the advisor is in a meeting, commuting, or at their desk.

How this shaped my approach

This project taught me that voice UX design is fundamentally interaction design for invisible interfaces — every state must be communicated through non-visual channels.

PRACTICE MANAGEMENT DASHBOARD

MyPractice

A financial performance command center for advisors to manage practice health, business performance, and client activity.

View Story