Project Summary
Prototyp is an AI-powered document review companion built for pharmaceutical proofreaders and editors. Developed as an internal pitch at a pharma advertising agency, the project started with working code and no UX foundation. The goal was to take a developer built AI algorithm and turn it into a human centered product experience from the ground up. The pitch received positive feedback and led to a referral for a follow-up pitch to another company.
Context » Internal pitch — Pharma Advertising Agency
Role » Product Designer(UX/UI)
Methods » User Research, Comparative Analysis, User Flow Mapping, Lo-Fi Prototyping
Inherited» A working AI matching algorithm with no UX or UI
Challenge» Define how automation could support proofreaders without disrupting a highly regulated review process
Project Goals
BUSINESS
Reduce time spent on claim verification
User
Eliminate manual document searching and claim matching
Design
Adapt an AI algorithm into a UI without disrupting existing workflows
Success
Faster verification, lower cognitive load, reviewer confidence maintained
Hypothesis
If we integrate AI directly into the existing proofreading workflow, we can reduce the time spent manually searching historical documents without disrupting the human review process.
the Problem
Problem Statement
Research Snapshot
Proofreaders and editors use project management and document editing tools like Workfront that were designed for general workflows. None of the tools in their existing process were built to handle the specific demands of pharmaceutical claim verification.
The current process required pulling previous brand campaigns individually and manually cross referencing language to determine if new claims would pass regulatory approval. The volume of documents involved made this the most time consuming and error prone part of the entire workflow.
For adoption to work, the AI could not disrupt the existing workflow. Prototyp needed to slot into the process at the exact point where manual searching happened, replacing that step without requiring users to change how they worked around it.
Workflow (Current)
Design Guidelines
Design Solution
Mapping the user flow with the team revealed the scope of what Prototyp could be. The original vision included document upload, matching, and editing in a single platform. Doing a comparative analysis of Adobe Acrobat, a tool already embedded in the proofreading workflow, and Grammarly, for its approach to organizing document views and surfacing results, provided the UI foundation. Patterns from both were adapted to reduce onboarding friction and make the experience feel like a natural extension of what users already knew.
User flow (Current)
Concept Pitch
The working prototype was presented to a pharmaceutical executive as part of an internal pitch, resulting in positive feedback and a referral to pitch the concept to another company. Following the presentation, a stakeholder recommended narrowing the scope. The original all in one platform vision would focus on what Prototyp did best, automating the document matching process. Document editing would remain in existing tools, repositioning Prototyp as a companion rather than a replacement.
User flow (Post Pitch)
The team aligned on Prototyp operating as separate but complementary system. Prototyp would own only the matching and review experience. No comments or annotations would live in Prototyp.
A critical insight from the session was how reviewers actually approach a document. The primary questions are always what's new and what's different. This became the foundation for how matched claims and claims drift were surfaced for the interface.
Feedback on the match experience indicated that reviewers needed a split screen to compare documents side by side with historical claims, a zoom tool, and the ability to drag across the screen. Nothing beyond that. The feature set was kept deliberately minimal to support focused only reviewing.
Content and claims data was specific to each individual asset rather than aggregated across a job. The job code was established as the primary identifier, with edit functionality built into Prototyp to account for naming discrepancies.
Final Designs
The AI matching logic, refined and fine-tuned throughout the project, correctly surfaced historical claims against new documents, validating the core direction: AI-assisted claim verification could sit inside the existing review process without replacing human judgment.
The stakeholder confirmed that nothing comparable to Prototyp existed, and that it could be effective at meeting its intended purpose.
Key Takeaway
Designing for a regulated industry taught me that the hardest UX problem wasn't the interface. It was knowing where automation should stop and human judgment should begin. That line informed every decision from the user flow to the MVP scope. When the stakeholder pitch resulted in a recommendation to narrow focus, it confirmed that getting that balance right was the actual design problem all along.
Next Steps
The next phase would be to incorporate the feedback on the suggested pivot, updating the user flow and defining the visual style for UI components beyond mid-fidelity wireframes.
© 2025 Randy Friday. Connect with me via Linkedin