Projects I’ve Built
Interactive prototypes born from real user research and deep product thinking.
10+ experiments | Agentic workflows, RAG, prompt engineering, full-stack AI products
As a Product Manager, I don’t just ideate - I research and understand pain points, validate with users, and build high-fidelity interactive prototypes that bring the full product vision to life. These are the personal projects and prototypes I’ve built in the last 12 months using Cursor, Vercel, Claude, LangChain/LangGraph, RAG pipelines, and no-code + code hybrids. Many started as class projects/ weekend experiments and turned into full demos I’ve tested with real users. Scroll, click “Try the Prototype” and see the prototypes.
Agentic workflows, RAG, prompt engineering, full-stack AI Products
As a Product Manager, I don’t just ideate - I research and understand pain points, validate with users, and build high-fidelity interactive prototypes that bring the full product vision to life. These are the personal projects and prototypes I’ve built in the last 12 months using Cursor, Vercel, Claude, LangChain/LangGraph, RAG pipelines, and no-code + code hybrids. Many started as class projects/ weekend experiments and turned into full demos I’ve tested with real users. Scroll, click “Try the Prototype” and see the prototypes.
NXTai - AI-Powered Feedback Intelligence Engine
- Designed a Product Memory Graph that unifies scattered signals - support tickets, surveys, CRM notes, reviews, product backlog and strategy into one contextual knowledge layer.
- Engineered ROI-weighted prioritization that quantifies revenue risk, churn probability, and retention value for every feature request.
- Built closed-loop automation pushing ranked recommendations directly into Jira and Notion, eliminating manual triage cycles.
Feedback Sources Supported
10+
Architecture
Edge-First
NXTai - AI-Powered Feedback Intelligence Engine
- Designed a Product Memory Graph that unifies scattered signals - support tickets, surveys, CRM notes, reviews, product backlog and strategy into one contextual knowledge layer.
- Engineered ROI-weighted prioritization that quantifies revenue risk, churn probability, and retention value for every feature request.
- Built closed-loop automation pushing ranked recommendations directly into Jira and Notion, eliminating manual triage cycles.
Feedback Sources Supported
10+
Architecture
Edge-First
NXTai - AI-Powered Feedback Intelligence Engine
- Designed a Product Memory Graph that unifies scattered signals - support tickets, surveys, CRM notes, reviews, product backlog and strategy into one contextual knowledge layer.
- Engineered ROI-weighted prioritization that quantifies revenue risk, churn probability, and retention value for every feature request.
- Built closed-loop automation pushing ranked recommendations directly into Jira and Notion, eliminating manual triage cycles.
Feedback Sources Supported
10+
Architecture
Edge-First
TalentSphere - Agentic Career Intelligence Platform for New Grads
- Developed a multi-agent system that maps a candidate's background to best-fit roles, industries, and precise skill gaps using real market data.
- Built smart sourcing and matching that auto-generates tailored applications and personalized recruiter outreach that lands replies.
- Shipped end-to-end at a competitive hackathon from user research to working prototype in under 48 hours.
Time to Career Clarity
<60 sec
Workflows Automated
4
TalentSphere - Agentic Career Intelligence Platform for New Grads
- Developed a multi-agent system that maps a candidate's background to best-fit roles, industries, and precise skill gaps using real market data.
- Built smart sourcing and matching that auto-generates tailored applications and personalized recruiter outreach that lands replies.
- Shipped end-to-end at a competitive hackathon from user research to working prototype in under 48 hours.
Time to Career Clarity
<60sec
Workflows Automated
4
TalentSphere - Agentic Career Intelligence Platform for New Grads
- Developed a multi-agent system that maps a candidate's background to best-fit roles, industries, and precise skill gaps using real market data.
- Built smart sourcing and matching that auto-generates tailored applications and personalized recruiter outreach that lands replies.
- Shipped end-to-end at a competitive hackathon from user research to working prototype in under 48 hours.
Time to Career Clarity
<60 sec
Workflows Automated
4
Rotten Tom-AI-toes - Clinical AI Governance & Trust Scoring Platform
- Designed a structured evaluation wizard that produces a composite Freshness Score across accuracy, safety, fairness, compliance, explainability, and robustness.
- Built a foundation model leaderboard benchmarking 17+ models by clinical suitability with trends tracking over time.
- Engineered enterprise-grade dashboards with real-time risk gauges, radar charts, and score rings, inspired by Datadog and Palantir Foundry.
Trust Dimensions
6
Models Compared
17
Rotten Tom-AI-toes - Clinical AI Governance & Trust Scoring Platform
- Designed a structured evaluation wizard that produces a composite Freshness Score across accuracy, safety, fairness, compliance, explainability, and robustness.
- Built a foundation model leaderboard benchmarking various models by clinical suitability with trends tracking over time.
- Engineered enterprise-grade dashboards with real-time risk gauges, radar charts, and score rings, inspired by Datadog and Palantir Foundry.
Trust Dimensions
6
Models Compared
17
Rotten Tom-AI-toes - Clinical AI Governance & Trust Scoring Platform
- Designed a structured evaluation wizard that produces a composite Freshness Score across accuracy, safety, fairness, compliance, explainability, and robustness.
- Built a foundation model leaderboard benchmarking various models by clinical suitability with trends tracking over time.
- Engineered enterprise-grade dashboards with real-time risk gauges, radar charts, and score rings, inspired by Datadog and Palantir Foundry.
Trust Dimensions
6
Models Compared
17
Kindred - AI-Powered Therapist-Client Matching Platform
- Led product strategy for a fit-based matching engine scoring compatibility across four clinically-grounded dimensions: therapeutic style, primary focus, depth orientation, and identity & cultural fit.
- Conducted 25+ user research interviews across therapists and clients, validating that 80% of therapists run unpaid screening and lose $6K-$12K/year to mismatched referrals.
- Shipped a working intake prototype and live waitlist. Securing 2+ verbal pay commitments and clinical advisor buy-in pre-launch.
Matching Dimensions
4
Revenue Leakage per Therapist
$6K-12K/yr
Kindred - AI-Powered Therapist-Client Matching Platform
- Led product strategy for a fit-based matching engine scoring compatibility across four clinically-grounded dimensions: therapeutic style, primary focus, depth orientation, and identity & cultural fit.
- Conducted 25+ user research interviews across therapists and clients, validating that 80% of therapists run unpaid screening and lose $6K-$12K/year to mismatched referrals.
- Shipped a working intake prototype and live waitlist. Securing 2+ verbal pay commitments and clinical advisor buy-in pre-launch.
Matching Dimensions
4
Revenue Leakage per Therapist
$6K-12K/yr
Kindred - AI-Powered Therapist-Client Matching Platform
- Led product strategy for a fit-based matching engine scoring compatibility across four clinically-grounded dimensions: therapeutic style, primary focus, depth orientation, and identity & cultural fit.
- Conducted 25+ user research interviews across therapists and clients, validating that 80% of therapists run unpaid screening and lose $6K-$12K/year to mismatched referrals.
- Shipped a working intake prototype and live waitlist. Securing 2+ verbal pay commitments and clinical advisor buy-in pre-launch.
Matching Dimensions
4
Revenue Leakage per Therapist
$6K-12K/yr