Case Study

Capital One — AI-Powered Decision Support

Building Capital One’s first human-in-the-loop AI feature for its risk management platform and defining reusable interaction patterns for future AI systems.

Explainable AI AI Decision Support Enterprise Risk Cross-Functional Collaboration

Role Sole UX Designer

Domain Enterprise Financial Services, AI Risk Management

Tools Figma, Gemini

Overview

I designed and integrated an AI-assisted evaluation tool into Capital One's risk management platform to improve data quality at the point of entry. The work delivered a production decision-support feature and defined reusable AI interaction patterns to support consistency across future features in the platform.

Traditional Workflow

Analysts were responsible for writing complex control descriptions that had to satisfy evolving compliance requirements. Quality issues were often identified only after submission, creating a reactive workflow that required revisions after Reviewer analysis. This delayed validation increased uncertainty, slowed delivery, and allowed quality issues to propagate downstream.

Compact vertical workflow showing reactive review steps — **Workflow Audit:** Mapped the baseline review process to highlight points where delayed validation created costly downstream revision cycles.

AI-Assisted Workflow

I redesigned the workflow by embedding AI evaluation directly into the authoring experience. Instead of discovering quality issues after submission, analysts receive immediate feedback while writing, allowing them to resolve issues earlier while preserving human decision-making.

Compact vertical workflow showing AI-assisted human-in-the-loop steps — **Human-in-the-Loop Architecture:** Embedded real-time AI evaluation into the authoring phase so analysts can resolve data quality issues prior to formal submission.

Design Strategy

The AI interaction model was guided by four design principles. Each principle was translated into concrete interaction patterns that balanced usability, explainability, and responsible AI communication.

Design Principle	UI Implementation
Embed AI into the workflow	Integrated AI evaluation directly into the authoring experience instead of a separate workflow or chat interface.
Communicate AI responsibly	Defined AI confidence, scope, status terminology, and color semantics to communicate AI findings without implying certainty or correctness.
Support informed decision-making	Designed per-criterion explainability, attribution, and supporting evidence to help analysts understand and verify AI recommendations.
Establish reusable interaction patterns	Created consistent UI patterns that could support future AI capabilities across the platform.

Key Decisions

Analysis Placement

The AI evaluation was embedded directly alongside the authoring experience rather than presented as a separate workflow or chat interface. Analysts could review AI feedback while editing the control description, eliminating the need to switch contexts or navigate away from their work.

Split-panel interface with authoring form on left and AI evaluation report on right — **Unified Workspace:** Paired authoring forms directly with real-time AI evaluation to allow continuous inline reviewing without context switching.

Analysis Breakdown

The AI Analysis panel was organized into four sections, separating AI context, evaluation results, supporting attribution, and user feedback into a clear, structured workflow.

Note: Interface mockups and workflows shown here are simplified abstractions created to illustrate interaction principles and layout strategy. They do not reflect final production code or proprietary system data.

AI Analysis Panel annotated into four distinct sections — **Structured Information Architecture:** Divided the evaluation panel into distinct functional tiers including context, findings, policy references, and user feedback—to aid quick scanning.

AI Confidence Indicator

Presenting AI confidence as a progress bar and percentage blurred the distinction between confidence and analytical results already shown throughout the interface. High, Medium, and Low communicated the same information while keeping confidence as supporting context.

Comparison between percentage-based and qualitative confidence indicators — **Qualitative Confidence Framing:** Replaced numerical percentage meters with qualitative confidence tiers to prevent users from confusing model certainty with empirical data metrics.

Per-Criteria Status Indicators

Control descriptions were evaluated against multiple quality criteria. The AI generated a report showing whether each criterion was detected within the description.

Status Indicator Terminology

Multiple terminology options were evaluated to communicate AI evaluation without implying certainty or correctness.

Option	Consideration	Result
Pass / Fail	Implied a final judgment.
Present / Missing	Described the criterion rather than the evaluation.
Found / Not Found	Resembled search results.
Detected / Not Detected	Framed the result as an evaluation rather than a definitive system status.	✓ Final

Status Indicator Colors

Multiple color options were evaluated using established UI semantics to reinforce AI evaluation without implying success or failure.

Option	Consideration	Result
Green / Red	Implied success and failure.
Blue / Orange	Communicated information and warnings.	✓ Final

AI Analysis card displaying status terminology and color semantics — **Responsible Status Semantics:** Paired "Detected / Not Detected" terminology with blue and orange status colors to communicate analytical findings without implying pass/fail judgment.

Per-Criteria Explainability

User research showed that AI findings alone were insufficient. Analysts wanted to understand how each conclusion was reached before acting on the recommendation. An on-demand explanation experience provided AI conclusions, supporting evidence, reasoning, and policy context without overwhelming the primary interface.

AI Analysis panel with connected on-demand reasoning overlay modal — **On-Demand Explainability:** Created a drill-down reasoning modal that surfaces model conclusions, supporting evidence, and policy context without cluttering the primary view.

Impact

Qualitative Outcomes

Analysts incorporated the reasoning modal into their review workflow before making final decisions.
Stakeholders reported improved clarity and faster review of AI-generated evaluations, with informal feedback indicating meaningful efficiency gains.
Engineering handoff was completed on schedule, including full specifications for the reasoning modal and associated UI components.

Reflections

Formal post-launch measurement was not in place, so long-term impact was not quantified at scale.
Future work would include lightweight instrumentation earlier in the build process to capture usage and decision signals prior to launch.
The primary constraint was not feature capability, but how AI outputs were structured and interpreted within the workflow.