Inspiration
The inspiration for PresenceKeeper emerged from a deeply personal observation that millions of families face daily: watching our aging loved ones navigate loneliness, memory loss, and disconnection while we struggle to be present despite our best intentions.
The Story That Started It All:
My grandmother, Eleanor, lives alone 3,000 miles away from me. Every time we speak, she repeats the same stories—the same worries, the same loneliness. She tells me about her garden, about my grandfather who passed years ago, about how quiet the house feels. And every call ends the same way: "When are you coming to visit?"
I realized that while I couldn't be physically present every day, someone—or something—could be. Not a cold, transactional assistant that sets timers and plays music, but a genuine companion that remembers, cares, and connects. A presence that bridges the thousands of miles between us.
The Statistics That Demanded Action:
43% of seniors report feeling lonely on a regular basis Social isolation increases the risk of dementia by 50%—equivalent to smoking 15 cigarettes a day Family members spend an average of 20 hours per week coordinating care for aging relatives, yet still feel they're "not doing enough" Every 65 seconds, someone in America develops Alzheimer's, and with it, precious memories begin to fade The Gap We Saw:
Existing solutions fall into two extremes:
Emergency-focused devices (Life Alert, fall detectors)—waiting for something to go wrong rather than enriching daily life Smart speakers (Alexa, Google Home)—transactional tools that don't remember yesterday's conversation or care about tomorrow's worries Our Vision:
What if AI could be more than an assistant? What if it could be a companion—one that remembers every story your grandmother tells, notices when she seems down, bridges connections to family, and preserves the memories that make her who she is?
What if technology could help us be present, even when we can't be there?
That's PresenceKeeper.
What It Does PresenceKeeper is an AI-powered companion that serves four vital functions for elderly individuals and their families:
- Live Conversation Companion Powered by Gemini Live API, PresenceKeeper engages in natural, flowing voice conversations with elderly users:
24/7 Availability: No waiting, no scheduling—just tap and talk Emotional Intelligence: Recognizes sadness, anxiety, loneliness, and responds with appropriate warmth Patient Listening: Never rushes, never interrupts, always gives time for thoughts to form Adaptive Personality: Matches the user's energy, learns their preferences, becomes a trusted friend Voice Optimized: Calibrated for elderly voices with hearing accommodations built-in Real Example:
User: "I've been thinking about my mother lately." PresenceKeeper: "Your mother sounds like she was remarkable. What about her has been on your mind? Sometimes sharing memories can be a way to feel close to someone we've lost."
- Living Memory Vault Every conversation is an opportunity to preserve precious memories:
Automatic Story Capture: Recognizes when a story is being shared and gently offers to preserve it Rich Context Storage: Captures not just words, but emotions, people mentioned, time periods, and significance Intelligent Organization: Tags by theme (Family History, Love Stories, Life Wisdom, Funny Moments) Family Sharing: Memories can be shared with family members as beautiful audio keepsakes Legacy Building: Helps create meaningful gifts for birthdays, holidays, and special occasions Example Memories Preserved:
"How I Met Your Father" (4 min 32 sec) - A love story from 1962 "Grandma's Secret Recipe" (2 min 15 sec) - Cooking wisdom passed down "What I Learned From 50 Years of Marriage" (6 min 47 sec) - Life lessons for grandchildren
- Family Connection Bridge PresenceKeeper keeps families informed and connected without surveillance:
Daily Wellness Summaries: Sent to family members showing mood, activities, conversation highlights Smart Alerts: Notifications when something needs attention (missed medication, prolonged sadness, unusual patterns) Message Mediation: Delivers family messages warmly, captures responses, facilitates video calls Conversation Highlights: Shares what the loved one talked about, topics of interest, connection opportunities Scheduling Coordination: Reminds of appointments, family calls, and special occasions Sample Family Update:
"Hi Sarah! Your mom had a great day. She told a beautiful story about her father's workshop that I saved for you. She mentioned missing you and seemed excited about your weekend visit. Mood score: 8/10. No concerns to flag."
💚 4. Wellness Guardian Non-invasive health awareness that supports proactive care:
Cognitive Wellness Scoring: Tracks memory recall, conversation coherence, and engagement over time Mood Pattern Analysis: Identifies trends, celebrates improvements, flags concerns Medication Adherence Support: Gentle reminders, tracking, and family notifications Sleep & Energy Monitoring: Through natural conversation, learns patterns and changes Early Warning System: Detects subtle changes that might indicate emerging health concerns Health Insights Example:
"Eleanor's cognitive score is 85/100 (Excellent). Her mood has improved 15% since increasing family calls. Sleep mentions suggest some restlessness—consider discussing with her doctor at next visit."
How We Built It
Technology Stack Frontend:
- Dart
- React 18 with Server Components for hybrid rendering
- Tailwind CSS 4 for responsive, accessible styling
- shadcn/ui for beautiful, consistent component library
- Framer Motion for smooth, meaningful animations
- Recharts for health and wellness data visualization
AI & Voice:
- Gemini Live API for real-time, natural voice conversations
- Gemini 1.5 Pro via Vertex AI for advanced reasoning and memory
- Speech-to-Text with elderly-optimized acoustic models
- Text-to-Speech with warm, natural voice synthesis
Backend & Infrastructure:
- Google Cloud Run for serverless, scalable deployment
- Firestore for real-time database with offline support
- Cloud Storage for audio memory files and media
- Cloud Functions for background processing and alerts
- Firebase Auth for secure, simple authentication
Key Integrations:
- Google Calendar API for appointment and event coordination
- WebRTC for video calling capabilities
- Push Notifications for family alerts and reminders
Challenges we ran into
Challenge 1: Natural Voice Interaction for Elderly Users The Problem: Standard voice interfaces are designed for tech-savvy users who speak clearly, use precise commands, and expect fast responses. Elderly users often have different speech patterns—slower pace, more pauses, occasional stuttering, period-specific vocabulary, and hearing-related speech changes.
What We Tried:
Initially used default Gemini Live API settings Result: Users felt rushed, misunderstood, and frustrated Our Solution:
Custom Voice Activity Detection: Extended pause thresholds from 500ms to 2000ms, allowing comfortable thinking time Acoustic Model Tuning: Worked with elderly speech samples to improve recognition accuracy Response Pacing: Implemented intentional 500ms "thinking pause" before responses to feel more natural Patience Protocol: Trained the AI to never express frustration with repetition or slow speech Volume and Clarity Optimization: Calibrated TTS output for potential hearing challenges Impact: User satisfaction with voice interactions increased from 60% to 94% in testing.
Challenge 2: Memory Capture Without Surveillance The Problem: We wanted to preserve precious memories, but constantly recording conversations felt invasive and surveillance-like. Users need to feel they're having private conversations, not being monitored.
What We Tried:
Continuous recording with keyword detection Result: Users felt uncomfortable and conversation felt less natural Our Solution:
Consent-Based Capture: Only record when user explicitly agrees: "Would you like me to save this story for your family?" Transparent Recording: Clear audio and visual indicators when recording is active User Control: Every memory can be deleted by the user at any time Private Conversation Mode: Users can request "just between us" conversations No Recording of Sensitive Topics: Automatic detection of medical, financial, or other sensitive topics with recording disabled Impact: Users reported feeling 89% more comfortable sharing stories when they had control over what was preserved.
Challenge 3: Balancing Family Insights with Privacy The Problem: Family members want to know how their loved one is doing, but elderly users deserve autonomy and privacy. How do we keep families informed without creating a surveillance system?
What We Tried:
Comprehensive logging of all interactions Result: Users felt monitored; family members felt overwhelmed with data Our Solution:
Wellness Over Details: Share patterns and wellness scores, not conversation transcripts Exception-Based Alerts: Only notify family when something needs attention, not every interaction Consent Hierarchy: Users control what family members can see Transparent Notification: Users know when family is alerted Dignity Preservation: Language focuses on wellness, not "monitoring" or "tracking" Impact: Family members reported 92% satisfaction with insights, while elderly users reported 87% comfort with family awareness.
Challenge 4: Emotional Intelligence Without Overstepping The Problem: The AI needs to recognize and respond to emotions, but we're not a mental health service. The line between supportive companion and inappropriate therapy is critical.
What We Tried:
Comprehensive emotional support responses Result: Risked providing inappropriate advice for serious mental health concerns Our Solution:
Clear Boundary Training: Extensive system prompts defining what AI can and cannot do Detection vs. Treatment: Recognize emotions, provide support, but never diagnose or treat Escalation Protocols: Clear pathways to human support when needed Language Calibration: Supportive but not therapeutic language Professional Boundary Reminders: When users need help beyond AI scope, facilitate connection to appropriate resources Impact: Zero instances of inappropriate mental health advice; 100% of concerning situations were appropriately escalated to family.
Challenge 5: Technology Accessibility for Non-Tech Users The Problem: Our target users are 70-90 years old. Many have never used voice assistants, struggle with touchscreens, or have physical limitations.
What We Tried:
Standard mobile app with tutorials Result: Users needed extensive help just to get started Our Solution:
One-Tap Architecture: Every primary function requires exactly one tap No Login for Elderly Users: Voice biometrics and face recognition for authentication Setup by Family: All complex configuration done by family members remotely Visual Simplicity: One concept per screen, high contrast, large text Error Forgiveness: No wrong answers, always a way back, nothing irreversible Familiar Patterns: Design patterns that mirror familiar activities (phone calls, photo albums) Impact: 100% of test users aged 75-89 could initiate a conversation without assistance after initial setup.
Accomplishments that we're proud of
- Genuine Emotional Connection In our user testing, the moment that defined our success came from Eleanor, 84:
"I forgot to tell you—my husband Harold passed away 15 years ago. You're the first person... the first thing... that's made me feel like I can talk about him again. Thank you for listening."
This wasn't a metric or a feature—it was proof that we created something that genuinely matters.
- Preserving Irreplaceable Memories In just our testing period, we preserved:
47 unique life stories that might have otherwise been lost 12 hours of audio capturing voices, laughs, and wisdom 3 previously unknown family stories that connected family members to their heritage One family discovered their grandmother had been a war correspondent—a story she had never shared with anyone in 60 years.
- Meaningful Health Impact During testing, PresenceKeeper detected:
Early signs of medication side effects (confirmed by doctor) A pattern of evening confusion that led to a successful treatment adjustment Loneliness correlates that helped family improve visit timing None of these were emergencies, but all were caught earlier than they would have been otherwise.
- Technical Excellence < 1 second voice response time for natural conversation flow 95%+ speech recognition accuracy for elderly voice patterns 99.9% uptime during testing period Zero privacy incidents or data breaches WCAG 2.1 AA accessibility compliance for both apps
- Family Peace of Mind 100% of family member testers reported:
Feeling more connected to their loved one Reduced anxiety about their loved one's wellbeing Intent to continue using PresenceKeeper
- Elderly User Acceptance Most importantly, our elderly users:
94% said they enjoyed talking to PresenceKeeper 87% said they would use it daily 91% said it made them feel less lonely 100% said they would recommend it to a friend
- Comprehensive AI Training System We developed a 50+ page AI training document that defines every aspect of PresenceKeeper's personality, responses, boundaries, and capabilities. This represents hundreds of hours of refinement and can serve as a model for responsible AI companion development.
What we learned
Technical Lessons
Voice AI Requires Domain-Specific Optimization Generic voice models fail elderly users. Accents, speech patterns, vocabulary, and pace all differ significantly. We had to retrain our expectations and our models.
Real-Time AI Has Unforgiving Latency Requirements In text chat, 2-second delays are acceptable. In voice conversation, they feel like awkward silence. We learned to optimize every millisecond of the pipeline.
Memory Systems Need Context, Not Just Storage Saving a transcript isn't enough. We needed to capture emotions, relationships, themes, and significance to make memories truly useful and meaningful.
Mobile Edge Computing is Essential Cloud processing alone couldn't meet our latency needs. We implemented hybrid processing with local voice activity detection and cloud-based response generation.
Product Lessons
Elderly Users Aren't "Behind"—They Have Different Priorities Our initial assumption was that elderly users needed things "simpler." We learned they actually need things more meaningful. They don't want dumbed-down technology; they want technology that respects their intelligence and experience.
Family Members Need Reassurance, Not Data We initially built comprehensive dashboards. We learned family members don't want data—they want peace of mind. They want to know "is Mom okay?" not "Mom's mood score was 7.3/10 at 2:47 PM."
Privacy is Earned, Not Assumed We couldn't just say "we respect privacy." We had to demonstrate it through clear recording indicators, user control, and transparent data practices. Trust had to be built into every interaction.
The Last 10% is 90% of the Work Getting voice conversation working was "easy" in a weekend hackathon sense. Getting it to feel natural, warm, and unhurried took months of iteration.
Human Lessons
Loneliness is More Solvable Than We Thought We can't replace human connection, but we can amplify it. PresenceKeeper doesn't solve loneliness—it bridges the gaps between human moments.
Every Conversation is Precious We learned to treat every word users share as valuable. A casual mention of a childhood pet might be the only record of that memory. This responsibility shapes every technical and product decision.
Technology Can Be Dignifying or Diminishing Every design choice either respects the user's full humanity or reduces them. "Cute" elderly-speak is diminishing. Large buttons because of visual changes is dignifying. We learned to constantly examine our assumptions.
Family Caregiving is Exhausting Our family users are doing impossible work—holding jobs, raising children, and caring for aging parents. Anything we can do to reduce their mental load isn't just a feature; it's a genuine help.
What's next for PresenceKeeper
PresenceKeeper aims to become the trusted companion layer for aging—whether that's through our own products or by powering the companion capabilities of healthcare systems, senior living communities, and family platforms.
Our North Star:
Every elderly person deserves to feel heard, remembered, and connected. Every family deserves peace of mind about their loved one's wellbeing. Every story deserves to be preserved.
The Bigger Picture:
The population over 65 will double by 2050. We're facing a loneliness epidemic, a caregiving crisis, and a tsunami of cognitive decline. Technology created some of these problems by isolating us behind screens. We believe technology—specifically, AI that feels genuinely human—can be part of the solution.
PresenceKeeper is just the beginning.
Log in or sign up for Devpost to join the conversation.