Ancestra: An Empathetic AI Agent for Multigenerational Health
My Role
Conversational AI/UX Designer
Team
4-person design team
Timeline
5 Weeks
Team
Overview
The agent proactively monitors patterns, adapts communication to individual needs, and integrates multimodal data (genetic, biometric, and historical) to deliver actionable wellness guidance.
My Role
As Conversational AI/UX Designer on a 4-person team, I shaped the agent's personality, tone of voice, and end-to-end conversational experience over a 5-week sprint.
The Problem
Modern medicine often overlooks the generational context; instead, it focuses on numbers and symptoms.
How Might We
Help users understand their current health patterns through the lens of lineage while keeping the focus on actionable present-day wellness?
Hypothesis
An AI agent designed with emotional intelligence, scientific rigor, and ethical data practices could help users understand "unexplained" symptoms through ancestral context by providing validation, insights, and actionable next steps.
Agent Design Process
How Ancestra.ai is built and how it helps users understand their health
01. Agent Design Architecture
We designed Ancestra.ai as a multi-layered AI system that goes far beyond a chatbot; it's an agent that observes, learns, and acts on behalf of user wellbeing.
Data Privacy Layer
User data remains encrypted
Users can delete everything instantly (actual deletion, not just flags)
Zero third-party sharing without explicit per-instance consent
02. Personality Traits & Tone of Voice
Traits deliberately avoided: clinical detachment that feels robotic, excessive optimism that dismisses real concerns, false certainty that overpromises what genetics can predict, and judgment about user choices or family history.
Protecting people from risk of being scammed by enhancing psychological safety
Shifting LinkedIn's user behaviour from flagging bad to identifying real
Building confidence in professionals as well as in their own network
Building confidence in professionals as well as in their own network
Building confidence in professionals as well as in their own network
Building confidence in professionals as well as in their own network
Building confidence in professionals as well as in their own network
Building confidence in professionals as well as in their own network
03. Guided Onboarding & Context Building
Ancestra.ai begins by gathering deep personal, family, and health context, from primary concerns to ancestral patterns and existing data. This ensures insights are built on a complete picture, not assumptions.
04. Intelligence Capabilities
Traditional health AI is reactive; users ask questions, and AI responds. Ancestra is an intelligent health partner that actively notices patterns, initiates meaningful conversations, and coordinates real healthcare actions.
Retrospective
Designing UX for AI isn't just about making something intelligent, it's about making it something truly useful and actionable in real situations.
Key Learnings and Reflections
Early engineering involvement
Bringing engineers into design reviews early, not just at handoff, surfaced technical constraints sooner and shaped better decisions.
Proactive gap filling earns trust
Stepping in to help configure blocked infrastructure, rather than waiting, built credibility with the wider team.
Stakeholder buy-in requires user evidence
Translating user quotes into concrete impact was what actually secured approval to move forward.
User feedback drives product vision
Active listening during research uncovered opportunities well beyond the immediate scope of the project.
Ancestra · An Empathetic AI Agent for Multigenerational Health. Let's make some magic happen — thank you for reading.