WorkAboutLifeContact
AI-Assisted Financial Advisory Workspace
An AI-powered workspace for financial advisors that uses LLMs to draft communications, summarize portfolios, and flag compliance risks - with built-in trust and verification patterns that keep advisors in control.
Client
Fidelity Investments
Role
Senior Product Designer
Timeline
4 months
Platform
Desktop + Mobile
Domain
Fintech / AI
Year
2024
The Challenge
Fidelity's financial advisors manage hundreds of client relationships simultaneously. Each client conversation requires hours of preparation - reviewing portfolio changes, drafting personalized communications, checking compliance requirements, and synthesizing market data into actionable insights. With the emergence of large language models, there was an opportunity to dramatically reduce this cognitive overhead.
But the core design challenge wasn't "how do we add AI?" It was "how do we add AI that advisors actually trust?" Financial advice is high-stakes, heavily regulated, and deeply personal. A single hallucinated data point in a client email could trigger SEC violations, erode client trust, or result in unsuitable investment recommendations.
I led the end-to-end design of this AI workspace, drawing on my experience with LLM interface patterns at Modguard.ai, compliance workflows from Deutsche Bank, and my deep knowledge of Fidelity's advisor tools and scheduling systems.
Explore the Workspace
The Client Experience
The advisor workspace is only half the story. Clients interact with a mobile companion app that surfaces the same AI-prepared materials their advisor sees - portfolio summaries, meeting agendas, and secure messaging - creating a shared context that makes every conversation more productive.
This view shows what Priya Mehta sees on her phone before, during, and after meetings with her advisor.
Research & Discovery
73%
of advisors spend 2+ hours prepping for a single client meeting
Internal research, n=48
67%
said they'd use AI tools only if they could verify every claim before sending
User interviews, n=32
4.2x
more compliance violations in AI-drafted content vs. manually written
Modguard.ai benchmark study
61%
of advisor time on emails is spent on formatting, not substance
Workflow analysis, n=24
Advisor Personas
Rachel - The Veteran
18 years220+ clients
Skeptical of AI, values personal relationships. Needs to see AI earn trust gradually. Uses templates she’s refined over a decade.
Core Pain Point
Drowning in prep work but won’t sacrifice quality for speed
Amit - The Digital Native
4 years85 clients
Eager to adopt AI but worries about compliance. Growing book fast, needs efficiency gains yesterday.
Core Pain Point
Making mistakes on compliance reviews because volume outpaces bandwidth
Advisor Day-in-the-Life Journey
Key Design Decisions
Confidence Score Visibility
Every AI-generated element displays a color-coded confidence score (green ≥90%, amber 75-89%, red <75%) with expandable source citations. Low-confidence items auto-expand their sources so advisors see the reasoning immediately.
Impact
Advisor trust in AI outputs increased from 34% to 78% within 6 weeks of deployment
Hallucination Flagging Pattern
Inline hallucination markers highlight any claim the system can’t verify against source data. Flagged content is visually distinct and requires explicit advisor confirmation before inclusion. Pattern refined from 100+ Modguard.ai user interviews.
Impact
Reduced unverified claims in sent communications from 12% to 0.3%
Integrated Compliance Checking
Real-time compliance checking runs inline as advisors edit AI drafts. Regulatory rules are surfaced contextually with specific rule citations (e.g., ‘FINRA Rule 2111(a)’) so advisors understand why something was flagged - not just that it was flagged.
Impact
Compliance review time reduced from 24-48 hours to under 30 seconds per communication
Designed by Rebecka Raj, 2024
Concepts shown here are similar to but may differ from what's deployed in production. Built on research conducted across 100+ advisor interviews and refined through iterative testing with compliance stakeholders.
Back to Projects