Designing Trust: How I improved adoption of an AI native platform for Regulation SMEs
A system-level behavioral redesign that replaced a rejected Appian (low code platform) prototype with a human-in-the-loop platform built for high-stakes regulatory work.
Role
Product Designer
Duration
4 Months
Client
NDA
Status
Shipped
📌Executive Summary
Highly skilled banking SMEs rejected a technically accurate AI regulation change management tool because it disrupted their workflows, felt like a black box, and lacked user agency in a high-stakes environment. I pivoted the project from a simple UI facelift into a system-level behavioral redesign, utilizing psychology principles to build user trust and keep humans meaningfully in the loop.
Before vs after redesigning one of the major part of the workflow. Behavioral+interface changes
Overall Impact
👥The Team & Cross-Functional Collaboration
Enterprise design is a team sport. Here is how I collaborated across product, engineering, and client stakeholders.
I led the UX strategy and end-to-end product design, collaborating daily in an agile loop with:
Lead of Engineering & AI Lead
Aligned on LLM capabilities, token parsing limitations, processing latency, and platform constraints.
Tied user experience milestones directly to business metrics, compliance mandates, and deployment roadmaps.
Engaged directly through contextual inquiries, A/B testing, and ongoing validation loops to ground assumptions in real-world user workflows.
Aligning on system behavior and requirements during a working session with the client Product Owner, Director of AI, and Tech Lead.
🛑 Context: Extremely high risk ($) domain
Some information about a domain that I knew nothing about before this project
Every time the FDIC or SEC releases a new regulation document, Subject Matter Experts (SMEs) at large financial institutions undergo a grueling, manual workflow:
The cost of making mistakes is catastrophic. To put this in perspective, in 2024 alone, the SEC collected $8.2 billion in compliance-related penalties. Furthermore, governing bodies constantly alter the Code of Federal Regulations, while these financial institutions operate globally across overlapping jurisdictions.
The Proposed Solution
Our engineering team trained an AI model to automate this process. The AI broke down large documents into granular "obligations" and mapped them automatically. Instead of manual extraction, SMEs simply needed to review the AI's work and correct it where necessary.
The Problem: Technical Accuracy ≠ User Adoption
1
It didn't fit into their existing mental models or workflows.
2
They completely mistrusted the automated output.
3
They felt a lack of user agency to properly correct what the AI had generated.
4
It felt like it was slowing them down rather than speeding them up.
I was brought onto the team to solve this. This wasn't a system capability issue; it was a human-system interaction failure.
🔍 The Discovery: Diagnosing the Trust Deficit
The higher the risk of a domain, the more important it becomes to research before designing.
To understand the friction, I looked past standard feature requests and analyzed recorded sessions of Regulation Change Analysts (SME stakeholders) working on cases in their current Excel-based workflows versus our pilot application.
The initial Appian pilot interface layout: Dense data tables, not east to read or verify, and obscured data origin reducing trust in output.
Key Research Findings
The Excel Preference: SMEs had a deeply ingrained psychological preference for Excel during the Applicability Assessment phase. Despite Excel's heavy cognitive load and friction, it provided total layout visibility and control.
The Real Success Metric: While the business focused on reducing manual hours, the SMEs judged the platform strictly on error prevention and ease of correction because the penalty for errors is too high.
Interaction Fatigue: Each document produced hundreds or thousands of obligations. Reviewing and editing them one by one on our pilot interface was a tedious, frustrating task.
🧠 The Psychological Framework
Design is ultimately based on human psychology, and I'm a firm believer in relying on research when designing for the unknown.
Rather than treating this as a superficial UI issue, I conducted academic research into automated workflows. I mapped the user resistance to 4 core psychological phenomena widely documented in human-automation interaction:
💡The Strategy: Adapting to User Comfort And Designing 'Deliberate Friction'
Focusing only on optimizing for speed was hurting trust and accuracy. I proposed 2 main changes in the workflow to improve that.
Proposal 1: Allowing users to download the AI output as .CSVs to augment existing workflow rather than disrupting it completely
Proposal 2: Adding a second SME as a reviewer on each case to reduce chances of errors, implementing a mandatory "Mark as Reviewed" check on each line item
Workflow Augmentation
Export to familiar Excel layouts — no forced UI adoption
Deep links to exact source document sections for easier referencing
Intentional Friction Points
Reviewer + Approver collaborative workflow
Mandatory "Mark as Reviewed" on every AI line item (Active Monitoring)
These suggestions caused a split between the PM and Product Owner due to the additional work being added by the intentional friction points and extra SME involved.
I suggested a A/B test to see the impact of the implementations to resolve the conflict.
A/B Test To Resolve Conflict
Speed Focus Workflow
15% error rate
~80% faster case completion
Low user confidence
VS
Active Monitoring
>3% error rate
~50% faster case completion
Higher user confidence
Due to the high risk nature of the domain, the lower error rate was prioritized over the faster case completion rates.
🎨Design System Foundations
Typography, colors, and flexible components
With the behavioral strategy validated by data, we moved forward with designing and building the entire web application platform from scratch. I established a custom design system tailored for high-density enterprise data representation.
💻The Custom Product Redesign (Deep Dive)
This section goes through some design decisions I made in the user interface to help
Case Management Simplified
The existing prototype used a card layout which made it incredibly difficult to scan for information. SMEs look for specific keywords, jurisdictions, and mandates when picking or tracking cases.
AI Output Management
Traceability
Active Monitoring
Excel Integration
Reviewer - Approver Flow
For every AI-generated obligation, the UI displays the exact path of the document origin. Clicking it pulls up a split-screen viewport highlighting the exact source text inside the original PDF document, allowing easy verification.
Link to original source document for output verification
Visualizing Interconnected Data
Once the parsed obligations are mapped to a bank's existing internal compliance controls, each obligation can map to multiple controls, and vice versa. To showcase it, I created an interactive alluvial chart to give an immediate macro view of mapping density. Users can also click on individual ribbons to filter the work items instantly.
Interactive alluvial graph representing obligations mapped to control for the SME to review and approve
I also built out
Reference library: with a network information architecture to easily access all regulations, policies, controls and explore their relationships
Case management system: to refer to older cases, and for managers to overview
And some other screens as part of the case flow that aren't covered here.
🚀Measurable Impact & Outcomes (Post Redesign)
Ultimately, design needs to be supported through metrics
By pivoting away from a basic cosmetic interface update to a behavioral design transformation, the product delivered substantial human and business value upon final testing. This lead to an acceptance to adopt the platform by the client.
📉
12%
Human-in-the-loop principles implemented improved error catching.
📈
64 → 87
SUS score
(compared to pilot)
UI/UX changes implemented improved product usability rating
📈
60%
Due to AI augmentation of workflow and platform efficiency
🔮Key Takeaways & Lessons Learned
This was probably the most stimulated my brain has been cause I love a good challenge.
Measuring the right metrics
Initially the whole platform was being sold to the client as a way to speed up workflow, while the SME users judged the platform on trust and risk.
Designing for 'Human-as-editor' shift
With AI automating work, it's causing an interesting shift in users going from creators to curators of the output and UX needs to optimize for it
Enabling transitions from legacy platforms
Forcing specialized users to immediately abandon a legacy software, causes instant psychological rejection regardless of how much better a new platform is. Adoption needs to be designed for and made smoother.
Let's talk design
I'm always looking to connect with interesting people
©2026 Tanay Arora.
~Life is too short to eject USB safely