CONTEXT
PROBLEM
RESEARCH
PROCESS
SOLUTION
IMPACT
REFLECTION
CONTEXT
Emotive Health — AI Scribe for Clinical Counselling
MY ROLE
Head Product Designer
TEAM
Product Manager, Clinicians
TOOLS
Figma, User-Interviews,
Emotive Health is a digital health platform designed to support counselling clinicians during live patient sessions. The core product is an AI-powered scribe tool that listens to therapy sessions, generates structured clinical notes, and produces compliant session reports that meet professional and accreditation standards.
My Role: As the designer, I worked closely with the founder and product manager on shaping the end-to-end Emotive Health applicatio, from the live session experience to reporting, clinic oversight, and operational scalability. Understanding integrations with US healthcare infrastructure such as EHR systems and insurance providers.
CONTEXT
PROBLEM
RESEARCH
PROCESS
SOLUTION
IMPACT
REFLECTION
PROBLEM
Tedious Workflows Hindering Efficiency
Clinical note-taking during counselling sessions is time-consuming, cognitively demanding, and often interrupts the therapeutic relationship. Clinicians are required to:
Capture accurate, structured notes
Track client progress over time
Overall clinic and organisational standards
Scale across individual clinicians and enterprise-level organisations
Meet strict documentation standards
Support compliance for audits, insurance, and accreditation
At the same time, organisations need visibility into:
Session quality and consistency across clinicians
Client progress and outcomes
The problem was how to design an AI-driven system that:
Reduced the mental load on clinicians during sessions
Maintained patient trust and confidentiality
Integrated seamlessly with existing healthcare infrastructure
CONTEXT
PROBLEM
RESEARCH
PROCESS
SOLUTION
IMPACT
REFLECTION
RESEARCH & INSIGHTS
We focused on understanding both clinical workflows and operational requirements across different scales of practice. Luckily we had direct access to a number of professional working in the field we could contact during this research discover phase and on-going iterations.
Key inputs included:
How clinicians currently take notes during sessions and the pain points involved
Common clinical documentation frameworks used in counselling (e.g. SOAP, DAP, BIRP)
Sensitivity around recording, privacy, and perceived “surveillance” during therapy
Clear control over what was captured and what could be redacted
“How can I make sure sensitive information won’t be exposed?”
Social and environmental factors (captured via ICD-10 Z-Codes) were often under-documented but critical to care quality
“Can the system identify and recommend various Z-Codes?”
Organisational requirements for quality assurance, reporting, and compliance
US-specific healthcare constraints, including EHR systems and insurance documentation
Several insights shaped the direction:
Documentation needed to be adaptable to different therapeutic frameworks
“I use SOAP but I know other counsellors will use their own system…”
Larger organisations required visibility without micromanagement
“How can I track progress across multiple clinics ?”
Clinicians wanted the tool to be present but invisible during session
“I don’t want to be interrupted during the session”
CONTEXT
PROBLEM
RESEARCH
PROCESS
SOLUTION
IMPACT
REFLECTION
PROCESS
Lean, iterative approach
The design process focused on balancing clinical empathy, technical complexity, and regulatory requirements.
Early work centred on mapping:
A live session flow that felt calm, unobtrusive, and clinician-controlled
Post-session workflows for reviewing, editing, and approving notes
Organisational views for supervisors and operations teams
Key considerations throughout the process included:
Designing for multiple user types: clinicians, supervisors, and administrators
Supporting both solo practitioners and large organisations with many clinics
Ensuring AI outputs were transparent, editable, and auditable
Prototypes were iterated to test how clinicians interacted with the scribe during real sessions, how comfortable they felt with the “listening” state, and how easily they could review and finalise documentation afterward.
CONTEXT
PROBLEM
RESEARCH
PROCESS
SOLUTION
IMPACT
REFLECTION
SOLUTION
The final product delivered a comprehensive AI scribe and clinical management platform, centred around trust, clarity, and scalability.
AI Scribe & Session Experience
Live session listening with a darkened, low-distraction interface
Clear confirmation states so clinicians could trust the system was active
Complete transcript with speaker recognition to distinguish:
Clinician vs patient
Ability to handle multiple speakers in group sessions
Automatic redaction of sensitive information, with manual override controls
Clinical Notes & Reporting
Generated structured notes aligned with; SOAP, DAP, BIRP and custom templates
Produced session reports that met accredited clinical documentation standards
Supported tracking of patient progress across sessions
Automatic detection and suggestion of relevant ICD-10 Z-Codes
Z-Codes used to surface social, environmental, and psychosocial factors
Enabled tracking and suggestion of case management referrals based on identified needs
Operational & Organisational Views
Tools to observe:
Individual clinician activity and quality
Patient engagement and outcomes
Clinic-level and organisation-level performance
Designed to scale from solo practitioners to large multi-clinic operations
Browser Plugins
Firefox and Chrome extensions allowed clinicians to start sessions instantly
Removed the need to log into the main platform for every session
Reduced friction at the moment where sessions begin
CONTEXT
PROBLEM
RESEARCH
PROCESS
SOLUTION
IMPACT
REFLECTION
IMPACT
The Emotive Health application significantly reduced administrative burden while increasing documentation quality and consistency.
Key outcomes included:
Clinicians could remain fully present with patients during sessions
Documentation quality improved through structured, compliant outputs
Organisations gained visibility into clinical quality without disrupting care
Z-Code support enabled better recognition of non-medical factors influencing health
Faster session start times through browser plugins improved adoption and usage
The platform successfully bridged clinical care, compliance, and operational oversight within a single system.
CONTEXT
PROBLEM
RESEARCH
PROCESS
SOLUTION
IMPACT
REFLECTION
REFLECTION
This project highlighted how sensitive healthcare tools must prioritise trust, transparency, and user control — especially when AI is involved. Designing a system that listens to deeply personal conversations required careful consideration of perception, ethics, and clinician confidence.
Designing for both solo clinicians and enterprise-scale organisations required careful abstraction: the same core data needed to tell very different stories depending on who was viewing it. Integrating clinical standards, EHR systems, and AI intelligence into a coherent experience highlighted the importance of strong information architecture and restraint in UI.
Ultimately, the project demonstrated how AI can meaningfully support clinicians, not by replacing judgment, but by removing friction from the work that surrounds care.
67%
improved patient interaction with scribing
42%
reduction in no-shows and cancellations
28%
reduction in unmet mental health needs by actioning social needs