Thread Medical | Note editing & Note inbox redesign

Redesigning the AI medical scribe tool for trust, usability, and clinical fit

Redesigning the AI medical scribe tool for trust, usability, and clinical fit

Redesigning the AI medical scribe tool for trust, usability, and clinical fit

PROJECT & TIMELINE

Feature refinement project


May 2022 - Aug 2022

MY ROLE

UX design and research intern, project lead
Collaborating with: Founders, 1 Product director, and 1 Engineer

MY CONTRIBUTION

User interviews
Competitor analysis
Product thinking
Wireframing
Prototyping & Testing

Overview.

Overview.

Thread Medical is an AI-powered medical scribe tool that takes care of the clinical notes, it transcribes doctor–patient conversations into structured clinical notes. It helps small and midsize practices reduce documentation time, minimize admin burden—without the need for manual note-taking or hiring scribes.

I led the redesign of the Arrival Notification feature, which business owners use to inform customers when their orders are ready for pickup. As order volumes grew, the original tool struggled to keep up. Notifications were delayed or skipped entirely, leading to missed pickups, product spoilage, and rising customer complaints.

Reduced physician documentation time with streamlined note generating, editing experience and a robust note inbox.

CHALLENGES & OPPORTUNITES

Beyond basic functionality — refining for clinical fit

Beyond basic functionality — refining for clinical fit

Thread Medical’s MVP offered basic functionality: recording, transcribing, and a simple chronological note inbox. However, the product faced key challenges in meeting real clinical needs and establishing credibility. It lacked the flexibility and workflow alignment clinicians needed.

Our goal was to enhance core features by understanding how physicians interact with notes before, during, and after patient encounters—guided by user research and user testing feedback.

BEFORE THE ENCOUNTER

Prepare
  • View patient history or previous notes

  • Scan for key issues or follow-ups

  • Identify areas to address during the visit

DURING THE ENCOUNTER

Capture
  • Start recording at the beginning of the visit

  • Engage with the patient naturally while Thread Medical transcribes in real-time

AFTER THE ENCOUNTER

Review & Finalize
  • View AI-generated clinical note

  • Copy the note into the EHR system

  • Make edits to match clinical standards or billing requirements

Note inbox listing notes choronogically

Recording and transcribing conversations into note

DISCOVER

Understanding the problem space

Understanding the problem space

To understand barriers to market fit and clarify the needs of target users, I synthesized past research and conducted a preliminary competitor analysis during the first two weeks.

While awaiting pilot user interviews, I collaborated with the team to compile a research plan and draft a guideline for conducting in-depth interviews to make sure the research goals are clear with our limited timeframe, while also seeking resources to better understand how AI conversation recognition works.

Key pain points and feature gaps were identified through user interviews

Key pain points and feature gaps were identified through user interviews

📝 Lack of editability causes trust issues

The inability to edit AI-generated notes creates friction:

  • Users are uncomfortable signing off on autogenerated notes they can't correct.

  • There’s a strong need for customization, including note formatting and reusable templates tailored to clinic or personal preferences.

📑 Users need efficient way to manage all notes

Current tools lack an efficient note inbox for quickly locating and managing notes, which slows down workflows in busy clinical settings. Users need:

  • A summary view of patient info before visits to prepare efficiently.

  • A quick way to create, locate, and revisit notes, especially when managing multiple patients.

  • The ability to revisit and update notes over multiple days due to evolving case details or staggered documentation time.

⛓️‍💥 Non-standard note format slows adpotion

Users are already familiar with their current EHRs. When the generated notes don’t follow expected structures:

  • It increases mental load.

  • Users are slower to adopt the tool, or revert to manual documentation.

🔌 Lack of Integration Slows Down Workflow

The current product operates in isolation from existing systems:

  • Users want seamless integration with their EHRs to support sign-off and billing processes.

After presenting the interview insights to the team, we identified two critical pain points that, if addressed, would have the greatest impact on the overall product experience:

After presenting the interview insights to the team, we identified two critical pain points that, if addressed, would have the greatest impact on the overall product experience:

The RICE scoring model helped us to prioritize the user needs considering the limited timeframe and engineering resources at hand.

📒 Takeaways.

📒 Takeaways.

Work within constaints. Design for the capability

Work within constaints. Design for the capability

During my internship, the greatest challenge was the limited time frame for organizing complex information and creating experience for a new feature. The team expected me to quickly integrate into the design process. It forced me to prioritize and make efficient decisions to deliver the MVP effectively.

While it was tempting to explore all possibilities of new features that could enhance the overall user experience, I had to ensure that the designs I proposed were feasible within the team's resources and capabilities. This experience taught me the importance of aligning design ideas with project constraints and making informed decisions that balance ideation with practicality.

Device-specific characteristics and user behaviors

Device-specific characteristics and user behaviors

Recognizing the importance of tailoring designs to specific devices, I learned to adapt my approach to accommodate user preferences and interactions on each platform. This insight has significantly influenced my subsequent design projects, as I now consider device-specific considerations to create optimal user experiences.

CHALLENGES

HMW deliver a robust experience that supports batch notification-sending while also allowing users to locate and notify specific orders more efficiently ?

HMW deliver a robust experience that supports batch notification-sending while also allowing users to locate and notify specific orders more efficiently ?