AI & Generative Intelligence Solutions
We design and deliver AI-first products using LLMs, conversational AI, and decision intelligence.
From emotion-aware voice systems to enterprise-scale AI platforms, these projects focus on real-world impact, scalability, and trust-driven automation.
Project details
- CTO / Product Lead
- AI & Generative AI
- 2025
ECQO – Conversational AI Podcast Host
Voice-First AI System for Early Mental Health Screening
ECQO is a conversational AI platform designed to deliver early-stage mental health screening through voice-based interactions. Instead of form-driven assessments, the system enables natural, podcast-style conversations that capture emotional nuance in a psychologically safe format.
The objective was to create an AI-native experience that lowers stigma, increases accessibility, and supports mental wellness — without crossing into clinical diagnosis or replacing professional care.
Problem & Opportunity
- Traditional mental health screening tools feel clinical and intimidating
- Text-based assessments fail to capture tone, hesitation, and emotional nuance
- Users frequently disengage before completing structured surveys
- This created an opportunity to design a voice-first screening experience that builds trust while preserving ethical boundaries.
Solution & Execution
- Built a conversational AI voice avatar powered by large language models (LLMs)
- Integrated speech-based emotion detection to enhance contextual awareness
- Implemented natural voice synthesis to ensure calm, human-like dialogue
- Designed short, structured podcast-style sessions to reduce cognitive fatigue
- Aligned system behavior with ethical guardrails and responsible AI principles
Impact & Outcome
- Lowered entry barrier for early mental health screening
- Increased user openness through natural voice interaction
- Improved session completion rates compared to traditional form-based tools
- Established scalable AI architecture for responsible early-stage assessment
What This Demonstrates
- Voice-first conversational AI system design
- Emotion-aware AI architecture in sensitive domains
- Ethical AI deployment within healthcare-adjacent environments
- Human-centered conversational UX at scale
- LLM-powered interaction frameworks with clinical boundary safeguards
Project details
- CTO / PM
- AI & Generative AI
- 2025
Lurqa – AI Companion App
Multimodal AI Companion with Emotional Memory Architecture
Lurqa is a 3D AI companion platform designed for sustained emotional engagement. The system combines voice interaction, long-term emotional memory, adaptive tone modulation, and visual embodiment to create a consistent and evolving AI presence.
The objective was to move beyond transactional chatbot experiences and build an AI companion capable of personality continuity and contextual awareness across sessions.
Problem & Opportunity
- Most AI companions frequently reset conversational context
- Emotional responses often feel scripted or shallow
- User engagement declines without sustained personality continuity
- This created an opportunity to architect an AI system that preserves memory, adapts tone, and maintains character integrity over time.
Solution & Execution
- Designed long-term emotional memory architecture to preserve interaction history
- Built dynamic tone modulation aligned with user intent (romantic, friendly, mentorship modes)
- Developed a 3D avatar layer to enhance presence and visual immersion
- Tuned LLM prompt frameworks for personality stability and narrative consistency
- Structured multimodal interaction flows integrating voice, memory, and visual feedback
Impact & Outcome
- Increased emotional attachment and user immersion
- Extended session duration and repeat engagement
- Delivered a personalized AI experience with sustained contextual awareness
- Established scalable foundation for long-term companion AI systems
What This Demonstrates
- Long-term memory architecture for conversational AI
- Multimodal AI system design (voice + avatar + LLM orchestration)
- Personality-consistent prompt engineering frameworks
- Emotion-aware interaction modeling
- Human-centered AI product development at scale
Project details
- Product Strategy / MVP Lead
- AI & Generative AI
- 2024 – 2025
Kwalifyr – AI Sales Copilot
AI-Driven Sales Intelligence for Founder-Led Startups
Kwalifyr is an AI-powered sales copilot designed to support founder-led startups in managing early-stage sales execution. The platform streamlines lead qualification, pitch preparation, and sales conversation refinement — positioning AI as an assistive intelligence layer rather than a replacement for human judgment.
The objective was to help founders accelerate revenue readiness without expanding sales headcount.
Problem & Opportunity
- Early-stage founders juggle product development alongside sales execution
- Inconsistent lead qualification leads to wasted cycles
- Sales insights and messaging are often fragmented across tools
- This created an opportunity to embed structured decision intelligence directly into the founder workflow.
Solution & Execution
- Designed AI-driven lead qualification frameworks to prioritize high-intent prospects
- Built structured pitch guidance flows powered by intelligent prompt orchestration
- Positioned AI as a copilot to enhance clarity and confidence in sales conversations
- Developed a founder-ready investor narrative and pitch materials
- Structured MVP architecture for scalable expansion into broader sales automation
Impact & Outcome
- Accelerated sales readiness for early-stage teams
- Improved clarity and consistency in founder-led sales conversations
- Strengthened investor-facing messaging and positioning
- Delivered a scalable MVP foundation for future product expansion
What This Demonstrates
- Applied AI for workflow intelligence in early-stage environments
- LLM-powered decision-support system design
- Productized sales enablement frameworks
- Founder-centric AI tool positioning
- MVP structuring for rapid validation and scaling
Project details
- Product & Documentation Lead
- AI & Generative AI
- 2023
Overjet – AI Dental Insurance Platform
Explainable AI for Dental Underwriting & Claims Decisioning
Overjet is an AI-driven dental insurance platform designed to enhance underwriting accuracy and streamline claims review workflows. Operating within a highly regulated environment, the system applies machine learning to support documentation analysis while maintaining transparency, auditability, and compliance.
The objective was to integrate AI into insurance decision-making in a way that augments human reviewers rather than replacing clinical judgment.
Problem & Opportunity
- Manual dental claims review processes are slow and inconsistent
- Underwriting decisions often lack standardized transparency
- Regulatory environments demand explainable, auditable AI systems
- This created an opportunity to deploy AI as a structured decision-support layer within compliant insurance workflows.
Solution & Execution
- Designed AI-supported underwriting and claims review workflows
- Established structured documentation frameworks to improve consistency
- Prioritized explainable AI outputs to support regulatory transparency
- Aligned system architecture with compliance, audit, and review requirements
- Ensured AI recommendations remained assistive rather than autonomous
Impact & Outcome
- Accelerated dental claim review cycles
- Improved underwriting consistency and documentation clarity
- Strengthened trust through explainable AI integration
- Platform recognized as a LinkedIn Top Startup
What This Demonstrates
- Explainable AI deployment in regulated insurance environments
- AI-assisted underwriting system design
- Compliance-first product architecture
- Human-in-the-loop AI integration
- Trust-centered automation in healthcare-adjacent industries
Project details
- AI Product & Strategy Contributor
- AI & Generative AI
- 2022 – 2023
BCG X – Enterprise AI Systems
Decision Intelligence & Pricing Optimization at Enterprise Scale
At BCG X, the engagement focused on building enterprise-grade AI systems for large retail organizations. The platforms supported pricing optimization, markdown strategy, and promotion planning across complex, high-volume product environments.
These systems leveraged large-scale datasets and decision intelligence models to improve commercial performance while integrating seamlessly into existing enterprise infrastructure.
Problem & Opportunity
- Retail pricing and markdown decisions often rely on static rules and manual analysis
- Promotion planning lacks real-time optimization capabilities
- Large enterprises require AI solutions that are stable, scalable, and integration-ready
- This created an opportunity to deploy production-grade AI systems that move beyond experimentation into operational impact.
Solution & Execution
- Designed and supported AI-driven pricing and markdown optimization models
- Structured promotion planning workflows powered by predictive analytics
- Ensured integration with enterprise data warehouses and operational systems
- Prioritized model robustness, reliability, and auditability
- Supported documentation and knowledge transfer for enterprise adoption
Impact & Outcome
- Enabled smarter, data-driven pricing decisions
- Improved promotion effectiveness and margin optimization
- Increased AI adoption within large retail environments
- Delivered scalable decision intelligence infrastructure
What This Demonstrates
- Enterprise-scale AI deployment in commercial environments
- Decision intelligence system architecture
- Integration-first AI engineering within legacy ecosystems
- Production-grade model reliability and robustness
- AI adoption enablement in large organizations