Back

AI Assistant for Advisers

Morningstar · Direct Advisory Suite

I designed the AI assistant inside Morningstar's adviser workstation, twice. First the beta that shipped. Then, from what the beta taught us, one assistant across the whole suite: it comes to where the adviser is working, answers with its sources, and never touches a client without a review, a receipt and an undo.

The Assistant page in Direct Advisory Suite with a greeting, a one-line brief, the chatbox and recent chats, a floating Why you are seeing this panel that explains a risk drift with its sources, and a receipt toast with an undo window
My role
Senior Designer, interaction model, design system and content
Company
Morningstar
Product
Direct Advisory Suite, the adviser workstation
Users
Financial advisers managing a book of clients, and their compliance teams

At a glance

The challenge
Advisers had the research, the tools and the client data, spread across a workstation with dozens of pages. Nothing told them what had changed for their clients that morning.
What I did
Designed the beta that shipped, then reviewed it in the wild, named six problems, and designed one assistant across the whole suite on the Morningstar Design System, down to thirty edge cases.
Where it landed
A beta that 34% of eligible advisers adopted. Then one assistant with three ways in, answers with sources, and nothing client-facing without a review, a receipt and an undo.
  • 34%adoption among eligible advisers during the beta
  • 45%fewer workflow steps from question to report
  • 3journeys shipped end to end in the beta
  • 56use cases mapped across the suite, 42 designed
  • 30edge cases designed before the happy path
  • 0client-facing actions without a review and a receipt

01 · Setting the scene

An adviser's morning, before the assistant

Direct Advisory Suite is Morningstar's workstation for financial advisers in the United States: clients, portfolios, the Screener, X-Ray, reports, research and news. Its home page was a news front page. Everything an adviser needed was in the product. Very little of it came to them.

The existing Direct Advisory Suite home: today's headlines with a large photo, a list of articles, two donut charts about the practice, and market indexes below
Before: news first, the practice second, and nothing about what changed today

The question every adviser asks each morning is "what changed for my clients, and what should I do about it?" The workstation could answer it, if the adviser already knew which fund was downgraded, which client had drifted, and which of twenty pages to open.

How might we

Give advisers an assistant that tells them what needs attention, answers in a shape they can check, and can act for them without ever acting without them.

I framed the work around three moments in the day, because each needs a different kind of help.

Morning

What changed?

A fund was downgraded. A client's risk drifted. The adviser has not asked yet, and should not have to.

Research

Find and compare

"Show me the top rated ETFs." The answer is a table to sort and take further, not a paragraph.

Client work

Do the task

A statement arrives as a PDF. Build the portfolio, check the risk, run a scenario, produce the report.

02 · My part in it

What I owned

I was the designer on the assistant from its first screens to the unified design: how it behaves before a question is asked, what an answer looks like, how one answer leads to the next, where it lives in the suite, and how it looks and speaks. I worked with the product and AI teams on what the model could reliably do, with compliance on what it was allowed to do, and with the design system team so that every screen reused library components.

03 · Act one: the beta

What shipped first

Four rules before any screen: bring the change to the adviser, answer with the product and not with prose, say what it means for my book, and show the working.

The home opened on a greeting, a prompt, and two modules that had already done the morning's work: Ratings Changes and Client Risk Fit Drift, ranked High or Medium by published scoring rules, with the exposure on every row. The assistant did not ask to be trusted; it showed the arithmetic.

The beta home inside Direct Advisory Suite: a greeting, a prompt box with attach and voice controls, five suggestion categories, a Ratings Changes module and a Client Risk Fit Drift module, and news for the practice below
The beta home: greeting, prompt, five ways to start, and two modules that rank what changed

Three journeys, one for each moment. "Show me the top rated ETFs" returned the Screener itself, with the steps it took and three follow-ups. A statement PDF became a portfolio, its X-Ray, a snapshot report and a crisis scenario, with the likely next step pre-filled in the prompt. A drift card opened a breakdown of which portfolio was driving it, then a rebalance recommendation.

One journey for each moment: a question, a file and a click, each ending in something the adviser can use

We chose to embed it in the suite rather than give it its own tab, by designing both to the same depth and comparing them on real screens. It shipped as a beta. 34% of eligible advisers used it, and the journeys cut the steps from a question to a report by 45%. That is where most case studies stop. This one turns here.

04 · The turn

Six things the live beta told me

Once it was live I went back through everything: seven Figma files, the beta itself, and my own review of its answers.

01

Context is the product

Advisers ask about the client or list on screen. Retyping a name into a separate chat was the top friction.

02

Answers changed shape

The same question, asked six ways, gave six different answers.

03

Claims without proof

Twice it said a comparison was ready and showed nothing.

04

The answer is not the end

The real job is the email, the proposal or the report that follows.

05

Compliance is a user too

Supervisors need what was said and done, for whom, from which sources, and who approved it.

06

Seven files, seven systems

Different headers, three purples, two typefaces, hand-drawn icons. None of it was the design system.

The review was the moment. I asked for the same thing six times, compare two portfolios, and got six different answers: prose, a tool with no summary, a promise with nothing behind it. So I wrote the answer I wanted as a template, and from then on treated the model's output as a design surface with a spec and a review.

Three of six attempts at the same question in the live beta

05 · The bet

One page, before any screen

The bet

An assistant that knows the adviser's book, cites every figure and drafts the next step for them to approve will give advisers their day back, without taking the decision away from them.

One assistant across the suite, three ways in: the Assistant page, a panel on the client, list or account already on screen, and one search box from anywhere. Every answer follows the same loop: plan, sourced answer, proposed action, adviser review, receipt with undo.

Designed for the lead adviser with 120 households, and shaped by the associate who does the bulk work, the compliance supervisor who approves it, and the firm administrator who sets the limits. Six hypotheses, each with a way to be wrong, and a map of 56 use cases, 42 of them designed, decided what went into the pilot.

06 · How I went about it

Six principles, two directions, one merge

01

Meet the adviser where they are

The assistant comes to what is on screen. The scope is always visible and always the adviser's choice.

02

No figure without a source

Every number carries its source and its as-of date.

03

Show the work

Long answers show the plan as they run. Partial answers say so.

04

End with a next step

Every answer offers one action, drafted and ready to review.

05

The adviser decides

Nothing reaches a client without approval, and every action has a receipt.

06

Quiet by default

The returning view is the chatbox and recent chats. AI styling marks only AI surfaces.

Then two whole directions to the same depth, 37 screens and 39, because the beta had taught me that a decision made on real screens does not get reopened. Option A kept the adviser's muscle memory and was easy to ignore. Option B turned answers into outcomes and felt like a different product. The final design keeps A's shell and B's behaviour.

Option A home: a centred greeting, the prompt, category buttons, and four module cards for risk drift, a ratings downgrade, research and market news Option B Today page: a morning brief with a five-minute prep button, KPI tiles, a ranked Needs you queue, today's meetings, market pulse and a list of work done overnight
Left: Option A, the familiar workspace. Right: Option B, a proactive Today page that ranks the work

The merge got one thing wrong. The Assistant page started as a ranked dashboard with nine action buttons above the fold, and it duplicated the suite's own pages. Four versions later it is just the chat, and the attention items moved to where the work is.

Four versions of the returning view listed as a table, with the chosen fourth version shown twice: the Assistant page with a greeting, one-line brief, chatbox, three suggestions and recent chats, and the same page with the search-or-ask box open
Four versions of the returning view, and the one that shipped: just the chat

07 · The walk: one adviser's morning

Notice, ask, answer, approve, receipt

This is where I spend most of the time in a walkthrough: one adviser, one morning, end to end.

She starts on the Assistant page

A greeting, a one-line brief ("Three things need you today, and you meet the Palmers at 11:00 AM"), the chatbox with three suggestions drawn from her book, and recent chats underneath. Nothing competes with the suite's own pages.

The Assistant page for a returning adviser: the AI mark and Good morning, Priya, a one-line brief, the chatbox with Skills and a sources chip, three suggested questions, and three recent chats with dates
The Assistant page: a greeting, a one-line brief, the chatbox, three suggestions and recent chats. Nothing competes with the suite's own pages

The assistant is already where she is working

Every workspace page has one Ask Assistant button, and the panel opens already scoped to what is on screen: all clients on the list, one household on the client page, one account on a portfolio. The scope is a chip she can see and remove. Attention items live here too, on the pages they belong to.

Carl Winslow's client page with the Assistant docked: key points about his risk and lake house goal, and three suggested questions A company stock account page with the Assistant scoped to the account: key points about NVDA concentration and questions about trimming, tax cost and the model
The same panel on a client page and on a portfolio page, scoped to each

The answer has a shape

A visible plan while it works, then a bottom line, short sections with a numbered source on every figure, a table of who in her book is affected, and three follow-ups written as the next thing an adviser would do. The same shape whatever the words, because that is what makes an answer checkable.

The assistant working on a question about Microsoft: a plan with three completed steps and one in progress, and a Stop button in the composer The finished answer: a bottom line, Morningstar analysis, market news, an Impact on your book table, numbered sources, feedback controls and three follow-ups
Left: the plan, visible while the assistant works, with Stop always available. Right: the answer it produces

Ambiguity gets a question, not a guess

"Compare port 1 with the model" matches three portfolios. The assistant asks with a choice card, then keeps the answer short in the chat and opens the full comparison in a canvas beside it, ready to export.

A clarifying choice card: three portfolios named Port 1, a Compare against field, an As of date, and Compare or None of these The comparison: a short bottom line and metrics table in the chat, and a canvas with allocation bars, trailing returns and shared holdings
Left: a choice, never a guess. Right: the chat stays short; the canvas holds the detail

An alert becomes an action, evidence first

"See why" on a drift alert opens the evidence before any action: the score over 90 days, the drivers and what each added, the sources, and a suggestion with its tax cost.

The Why you're seeing this panel: risk score rose from 47 to 56 in 30 days, a 90-day bar chart, what changed with three drivers and their impact, sources, a suggestion, and actions
Evidence before action: the trend, the drivers, the sources, then the choice

When she asks for a check-in email, the assistant drafts it and says "Nothing is sent until you approve it." The review shows the message, the attachment and the checks it ran. After approval, a receipt: drafted, pre-checked, approved, sent, logged, and an undo window of five minutes.

The Review email panel: recipient, subject, message, a rebalance proposal attachment, checks before sending, and Cancel, Edit in Outlook, Approve and send The receipt in the chat: email sent to Carl Winslow with four completed steps, attachment, CRM log and follow-up, three follow-ups, and an Undo toast with a countdown
Left: review before it is sent. Right: a receipt for every action, and five minutes to undo it

Twelve households, not one

The same journey for the twelve households that hold a downgraded fund. The assistant shows a plan before it writes anything, flags the three who hold more than 10% for a call instead, then lists every draft to approve one by one or all at once. Above ten households a second approver is built in.

Before drafting twelve notes the assistant shows the plan: twelve households that hold Core Equity Fund, the firm template, what is personalised, secure email from the adviser, approval by the adviser then a second approver, and three households flagged for a call The review panel for a market note to twelve households: a list of drafts with Ready or Call suggested status, a preview of one note with the personalised values highlighted, policy v7 passed 12 of 12, and buttons to approve nine notes or all twelve
Left: the plan, checked before anything is written. Right: every draft reviewed, with three held back for a call

08 · The rest of the week, and when it goes wrong

Other journeys, and thirty states beyond the happy path

The rest of the week follows the same loop: a daily brief that says what the news means for her clients, onboarding that shows her own book ranked within three minutes, a thumbs-down that drafts a support ticket in the chat, a library and a compliance console that keep every receipt, and a phone for the brief, approvals and a voice question before a meeting.

Four phone screens: Today with the needs-attention queue, Approvals with a check-in email and a rebalance proposal, a voice question about the Palmers, and lock-screen notifications
Today, approvals, a voice question and notifications

Trust is won or lost in the failure states, so I designed thirty of them before the happy path shipped: vague requests, missing or conflicting data, slow or broken systems, blocked or partly failed actions, the panel without a scope, and the empty page. Every one says what happened in plain words, keeps the adviser's work, and offers one next step.

Three of the thirty: when data conflicts, when compliance says no, and when a step fails halfway

09 · Making it real

One design system, one file, one voice

Every screen is built from the Morningstar Design System and its Foundation library, with the suite's own header and navigation, one condensed typeface, 1 px corners, neutral icons, and the AI mark only where it identifies the assistant. The three options live in one file: 101 screens, 159 components, 155 tokens.

A QA pass found grey text at 2.73:1 contrast, allocations that totalled 105%, a risk arrow pointing the wrong way and a hand-drawn copy of the AI mark, and each was fixed in the component. Every string follows one content style guide: the point first, one term per idea, buttons that say what happens, and an assistant that speaks as I and admits its mistakes.

The cover of the unified design file: the AI mark, Direct Advisory Suite, AI Assistant, Unified design system and flows, consolidated from seven files, and five counts: 155 tokens, 32 text styles, 159 components, 268 icons, 101 screens
The cover of the design file, with the counts that replaced seven separate files

10 · Where it stands, and what I learned

Results, targets, and the honest gaps

I left Morningstar in July 2026 while the assistant was in beta, so the numbers are from the beta period and the team's own reporting.

34%

adoption among eligible advisers during beta

45%

fewer workflow steps from question to report

3

journeys shipped end to end in the beta

The unified design is measured against targets I set for the pilot, not results: the north star is weekly active advisers who approve at least one assistant draft, with a sourced answer in under 60 seconds, a 12-household outreach in under ten minutes, every figure sourced, and zero unsupervised client-facing actions.

If I did it again

The most valuable thing an assistant can do is not answer questions; it is decide which questions are worth asking today. Start with what the product already knows.

Trust is a set of components, not a tone of voice. The plan, the sources, the clarifying card, the review, the receipt and the undo each answer a specific objection, and built as parts, every new journey arrives with trust already in it.

The home is not the product. A page that ranks everything looks powerful and competes with the suite it lives in. Quiet by default was the hardest principle to keep.

The model's answers, and the words around them, are part of the design. Writing the answer as a template and reviewing live output against it is the work I would start first next time.