Intuit: AI/ML Account Recommendation Redesign

Context

01 The Intuit Identity Platform

The Intuit Account Manager platform empowers customers to manage their data across the various Intuit products they use. It serves as a collaborative platform where identity management capabilities are contributed to provide customers with functionalities such as managing payment methods, sign-in and security, profile management, and more.

Customer insight

02 "I want guidance that actually applies to me, not generic reminders I start to ignore."

Feedback from over 140,000 customers stated that they see the same account prompts repeatedly, even if they did not apply to them. This created frustration and reduced trust in account-level messaging.

At the same time, the business needed a scalable, intelligent way to surface the right actions to customers across millions of account sessions, without increasing friction or requiring manual targeting rules.

The team opportunity: how might we use AI to help customers complete the right tasks at the right time? Intuit is prioritizing an AI-driven future, encouraging designers to identify opportunities where intelligence can enhance customer experiences. This shift enables the Platform team to move from rigid, rule-based logic to adaptive, data-driven models that learn from real behavior.

Design process

03 How I collaborated with stakeholders

• Data engineering capabilities Worked closely with data science to understand how the model made recommendations and where it could be inaccurate. This helped ensure the experience was clear, trustworthy, and not misleading to customers.
• Recommendation framework definition I created a structured system for how recommendations should appear based on themes I surfaced from customer VOC, and how messaging adapts based on user signals. This framework later scaled to additional account tasks I designed.
• Picked one task recommendation to test and validate We tested three messaging tones, trust-focused content cues, and visual hierarchy, because updating a phone number is a high-value action tied to sign-in, identity, and security.
• Pilot launch + measurement Launched with a focused pilot audience to measure real-world interaction patterns and optimize before broader rollout.

The framework

04 Five themes, built from Voice-of-Customer insight

We used Voice-of-Customer insights to identify the most common account tasks and grouped them into a set of simple, meaningful themes. I partnered with a Senior Content Designer to ensure the framework was easy to understand and supported clear, consistent messaging.

• Critical Tasks If the customer doesn't take action, will this compromise their security or identity?
• Celebrating Milestones If something is achieved, are we taking time to engage in celebratory moments?
• Product Features Not Being Utilized If the customer isn't aware of a feature and its benefit, did we inform them?
• First-Time Customers If I'm new to Intuit, what tasks should I be handling first before all others?
• Support, Retention & Revenue What tasks do I need to complete to prevent disruption of product use?

The test case

05 The task recommendation we tested

We identified a high-value identity task to redesign and measure that we were confident customers typically don't ignore. By analyzing customer account behavior, we selected the "Confirm your phone number" recommendation as a strategic task to introduce to the AI/ML model. It plays a critical role in account security, recovery, and user trust, making it an ideal test case to improve relevance, clarity, and completion rates using ML-driven insights.

• Before: generic prompts shown to all users After: personalized recommendations based on behavior and account state.
• Before: no explanation of why the prompt appeared After: clear contextual messaging explaining relevance.
• Before: repetitive experiences that led to frustration After: dynamic, adaptive recommendations that evolve over time.

Research insights

06 What we learned

Through usability reviews, customer feedback data, and behavioral analytics, we identified three key patterns that informed the design, both from logic and the presentation of the AI recommendations:

• Repetition drives dismissal when customers see the same prompt multiple times, they assume it's not relevant and stop trusting guidance. In pilot we observed a 30% drop in prompt dismissals (based on internal logs).
• Context matters customers respond better when the recommendation clearly explains why it's being shown. Customer feedback post-launch noted that the recommendation felt "clearer" and "more helpful".
• Identity-related tasks carry emotional friction updating account details (phone, email, password) requires trust. Customers need confidence that the prompt is legitimate and safe.

Takeaways

07 Trust, timing, and clarity matter more than volume

This project marked Intuit's first foray into embedding AI/ML into customer-facing platform experiences. Instead of hard-coded rules, the system now adapts to customer history, surfacing the most relevant task at the optimal time. Our design work not only boosted engagement but also revealed insights about how customers perceive value from AI recommendations: trust, timing, and clarity matter more than volume.

The results validated our direction and pointed toward opportunities for even more personalized, adaptive experiences going forward. This project stretched me in new ways. Stepping into that uncertainty helped me deepen my skills in AI-driven design, cross-functional collaboration, and creating systems that scale.

Key outcomes

08 The results at a glance

• 5% lift in task completion within 60 days of launch
• 30% drop in prompt dismissals during the pilot
• Influencing 21M+ annual Intuit Account visits
• Set the design principles for all future AI/ML account recommendations