COI360 - Intelligent Document Processing System
COI360 (formerly CTRAX) is an end-to-end compliance and document processing platform handling thousands of Certificates of Insurance (COIs) each month for agencies, ports, construction firms, school districts, cities, and more. In addition to verification, it manages policy tracking, expiry alerts, and audit reporting. This case study focuses on the verification workflow how we transformed a manual, error-prone OCR process into an AI-powered, user-centric experience.
Role
UX Researcher
UI Designer
Year
2025
Client / Company
Management Data Inc
Problem
The legacy OCR (Artsyl) delivered <50% accuracy, supported only ACORD 25, and couldn’t learn from corrections. Specialists spent 800+ hours/month on copy-paste workflows, context switching, and error-prone reviews without confidence scores or prioritization leading to fatigue, low morale, and compliance risks.
Solution
We reimagined verification with AI: flexible document classification, adaptive field extraction, and continuous learning. Intuitive UX with visual overlays, confidence heat-maps, inline editing, and robust ML models cut review time, reduced errors, and scaled seamlessly across evolving COI formats.
Impact
How might we transform the legacy OCR-based verification workflow into an AI-powered, user-centric experience that reduces manual effort, increases accuracy, and scales across diverse COI templates.
I aimed to gain a deep, empathetic understanding of specialists’ end-to-end verification workflows to surface both explicit frustrations and hidden challenges, and pinpoint critical UX pain points for targeted AI-driven solutions.
Spent two days observing three specialists processing live COIs in their natural environment. Logged every interaction, click, and hesitation; captured workarounds (e.g., sticky notes for reminders, printed spreadsheets for cross-checks).
Asked specialists to demonstrate the exact steps they take when verifying a COI in COI360, probing for pain points at each click focused on uncovering workflow gaps, decision criteria, and emotional responses rather than abstract preferences.
To better understand user frustrations with the old system, I created an Empathy Map. This helped capture what users say, think, do, and feel during the COI verification process. The map highlighted that users spent significant time manually transferring data from forms, double-checking every field, and struggling with poor scan quality. It also revealed their feelings of frustration, anxiety about errors, and lack of trust in system outputs. By visualizing these insights, we were able to connect user pain points directly to design opportunities for the new system.
After conducting contextual inquiries, I synthesized the findings into an affinity map. This helped organize scattered pain points into clear, actionable themes. By clustering similar insights, patterns began to emerge that revealed the underlying challenges in the current COI review process.
To humanize the research findings and ground design decisions, I synthesized insights from contextual inquiries, shadowing sessions, and interviews into a single representative persona.
Every document requires full review, consuming 800+ hours monthly.
Blurry, skewed scans from varied sourced equipments reduce OCR accuracy and create rework.
Without confidence indicators, ~5,000 forms are all reviewed equally.
All COIs are processed in order, with no risk or deadline prioritization.
Specialists juggle dozens of COI templates across tools, causing errors and fatigue.
OCR only supports ACORD 25, forcing manual extraction for all other forms.
Instrumented the prototype and legacy system with stopwatch timings across 20 COIs each. We measured durations for extraction review, correction, and save steps.
Instrumented both the prototype and legacy system with stopwatch-based time tracking across 20 COIs to measure performance. Recorded durations for extraction review, correction, and save actions revealing that specialists currently spend an average of 5–15 minutes per COI.
65%
Of total task time spent aligning data to form.
1-2m
Spent searching for paste targets.
We ran a sticky-note brainstorm with the verification team, 50+ ideas dot-voted and clustered into Visual Mapping, Smart Triage, Batch Efficiency, and Image Enhancement, then converged on the north-star concepts: inline overlays, confidence heat-maps, batch-edit panels, and AI template detection to cover every COI layout.
We began with paper Crazy 8s across core concepts (dual-pane mapping, inline overlays, confidence cues), converged the best ideas into a unified low-fi wireframe, and built a focused Verification prototype to align stakeholders on the core flow. With that validated, we moved straight to high-fidelity mocks, confident the foundation worked.
Dual‑pane overlays link each field to its exact spot on the PDF, so reviewers never lose context while verifying.
The AI classifier tags each upload by type the moment it arrives, eliminating manual sorting and guesswork.
Confidence badges and filters route only risky COIs to humans, letting clean files pass without extra effort.
Drag‑drop, email, and QR capture meet users where they are, accelerating intake and improving image quality.
We wanted to verify whether COI360 actually reduced effort compared to the existing system.
We created a dataset of 20 COIs that included a balanced mix of: 1. Clean digital PDFs 2. Low-quality scans 3. Multi-page forms 4. Hand-marked and difficult-to-read documents Reviewers were asked to verify all critical fields (insured details, policy numbers, coverage limits, dates, checkboxes, and Description of Operations) in both: 1. The existing system (legacy OCR + manual review) 2. The new COI360 flow For each document, we recorded the time on task from the moment a reviewer opened the COI to the point they confirmed it was ready for export.
We observed that Time on task reduced by ~50% across the dataset.
1. Vendor/Agent Portal – Secure uploads, live status tracking, and self-corrections for vendors. 2. Real-Time Compliance Pre-Check – Instant Pass/Warning/Blocker validation with fix prompts at upload. 3. Mobile Capture & Review App – Camera-assisted capture, offline support, and push-based re-submission.
“The new design simplified workflows, enhanced accuracy, and made compliance management more efficient”
Matthew Francis, Director of Sales at MDI