CARE by MarianaAI

AI Native Clinical Copilot for Documentation and Decision Support

CARE by MarianaAI Clinical copilot interface showing patient encounter workflow

OVERVIEW

Executive Summary

CARE is an AI native clinical copilot platform designed to reduce documentation burden, provide real-time decision support, and streamline downstream administrative workflows for healthcare providers. The product integrates directly with existing clinical systems and EHRs, enabling ambient documentation and AI assistance without disrupting clinician-patient interactions.

This project documents my work on the early design and foundational clinician experience for CARE, with a focus on workflow alignment, explainability, and scalable personalization across specialties. The goal was to design AI assistance that functions as background infrastructure supporting clinical work without adding cognitive or interaction overhead.

SCOPE

Scope of Work
Documentation

Clinician facing documentation and review workflows

Real-time Support

Real-time AI assisted decision support patterns

Human in the loop

Human in the loop control and validation

EHR Integration

UX considerations for deep EHR integration

APPROACH

Design Principles

The design approach centered on creating AI assistance that functions as background infrastructure supporting clinical work without adding cognitive or interaction overhead. Key principles guided the work:

Workflow Alignment

Designing AI features that integrate seamlessly into existing clinical workflows rather than creating parallel processes.

Explainability

Ensuring AI suggestions are transparent and traceable, building trust through clear reasoning and source attribution.

Scalable Personalization

Creating adaptive experiences that learn from individual clinician preferences while maintaining consistency across specialties.

Minimal Cognitive Load

Reducing interaction overhead so clinicians can focus on patient care rather than managing AI tools.

RESEARCH

Clinician Workflow Stages

The clinician workflow was mapped across the full encounter lifecycle to identify touchpoints where CARE could reduce documentation burden and support decision-making without disrupting patient interaction.

Appointment Scheduling1

Appointment Scheduling

Pre-Visit Chart Review2

Pre-Visit Chart Review

Clinical Encounter3

Clinical Encounter

Real-Time Documentation4

Real-Time Documentation

Orders & Follow-Ups5

Orders & Follow-Ups

Coding & Billing Tasks6

Coding & Billing Tasks

End of the Day Wrap-up7

End of the Day Wrap-up

RESEARCH

Encounter Journey Analysis

Before introducing CARE, we examined the clinician’s full workflow to understand where friction accumulates. The goal was to identify moments of high cognitive load and operational strain. The analysis revealed repeated context switching across scheduling, documentation, coding, and follow ups. Administrative tasks often extended beyond clinical hours.

The table below summarizes the key stages, actions, and pain points in the current experience.

Stage

User Actions

Touchpoints

Pain Points

Cognitive Load

1

Appointment Scheduling & Calendar Review

  • Review daily schedule
  • Assess visit types
  • Adjust for cancellations or overbooking
  • EHR scheduling module
  • Front desk coordination
  • Email/phone
  • Limited insight into visit complexity
  • Manual rescheduling
  • No predictive support for no-shows
  • Anticipatory stress
  • Planning overhead
2

Pre-Visit Chart Review

  • Open patient chart
  • Review prior notes, labs, medications etc
  • EHR patient chart
  • EHR Medication History
  • EHR Labs History etc
  • Information scattered across modules
  • No summarised patient snapshot
  • Time pressure between visits
  • Moderate cognitive load
3

Clinical Encounter

  • Conduct interview
  • Examine patient
  • Gather findings
  • Patient interaction
  • EHR
  • Physical Notes
  • Must mentally retain information while navigating EHR
  • Divided attention between patient and screen
  • High cognitive load
4

Real-Time Documentation During Visit

  • Enter symptoms
  • History
  • Assessment
  • Plan into EHR
  • EHR templates
  • Forms
  • Interrupts patient rapport
  • Rigid templates
  • Navigation friction
  • Frustration
  • Task switching fatigue
5

Coding & Billing Tasks

  • Select diagnostic and Procedure Codes
  • EHR coding module
  • Codes not surfaced contextually
  • Separate mental translation from note to code
  • Compliance anxiety
  • Administrative anxiety
6

Orders & Follow-Ups

  • Enter labs
  • Referrals
  • Prescriptions
  • Multiple EHR modules
  • Context switching across screens
  • Manual coordination for follow-up scheduling
  • Irritation
  • Friction accumulation
7

End of the Day Wrap-up

  • Sign off notes
  • Reconcile incomplete documentation
  • EHR dashboard
  • Backlog from earlier visits
  • Documentation spills into after hours
  • Fatigue
  • Burnout accumulation
Stakeholders Alignment

Cross-functional perspectives were gathered to clarify priorities, constraints, and success criteria across groups. Each function evaluates the product through a distinct lens, including clinical efficiency, system stability, financial performance, and scalability.

Key Findings

Stakeholder

What They Care About

Alignment Focus

Clinicians

  • Reduce documentation burden
  • Protect patient interaction
  • Structured documentation
  • Ambient AI
  • Minimal workflow disruption
  • Human control

IT / EHR Teams

  • Stable integration
  • System performance
  • Seamless EHR integration
  • Low technical overhead

Compliance / Billing Teams

  • Coding accuracy
  • Reduced denials
  • Structured data capture
  • AI-assisted coding

Executive Leadership

  • ROI
  • Scalability and Adoption
  • Measurable impact
  • Configurable platform

DEMO

Product Walkthrough

An interactive walkthrough of the clinician experience is available below, showcasing the core workflows and AI-assisted features designed for CARE.

CARE platform appointments interface showing patient list and calendar
Additional Details

Due to the sensitive nature of healthcare product development, detailed design artifacts and research findings are available upon request in a confidential context. Feel free to reach out at raza2393@gmail.com.