Faculty and STEM education
AI-literacy workshops
Hands-on programs in prompt design, source verification, model failure modes, assessment redesign, and evidence-based scientific judgment.
Computational chemist · Scientific AI builder · Principal investigator
Scientific AI, built to be inspected.
I help institutions, research teams, and science educators build AI systems and learning programs that preserve evidence, expose uncertainty, and strengthen human judgment.
Evidence → decision → audit
A shared discipline for products, agents, and research.
4M+
products scannable through Clarity
29K+
evidence-graded ingredient records
32
condition-specific decision dimensions
13
current public Constat MCP tools
Public product figures verified July 30, 2026.
Approach
Evidence is a product requirement.
I design scientific AI systems around a clear chain from source to decision. The data model preserves provenance. The interface exposes uncertainty. The release process tests whether the system still performs as claimed.
This discipline drives Health AI's product intelligence and MCP infrastructure, my research and teaching at Yeshiva University, and the workshops and partnerships I design for STEM organizations.
A model can produce an answer. A trustworthy system must also show why the answer deserves confidence.
Product and platform leadershipProblem definition, architecture, sequencing, business model, and delivery.
AI deploymentWorkflow design, technical implementation, adoption, and controlled release.
Evaluation and trustProvenance, evidence tiers, ambiguity handling, monitoring, and claim limits.
Scientific leadershipComputational chemistry, experimental design, research programs, and translation.
AI literacy and learning designWorkshops and curricula that make model evaluation, source verification, and scientific judgment visible.
Engagements
AI capability for people who answer to evidence.
I work with universities, research groups, scientific organizations, and product teams that need practical AI adoption without losing disciplinary rigor.
Research institutions
AI-for-science strategy
Tool evaluation, workflow design, reproducibility controls, evidence capture, and human-review architecture for research teams adopting frontier AI.
Organizations and product teams
Scientific AI advisory
Product and evaluation strategy for high-consequence systems: scope, evidence models, claim limits, governance, and controlled release.
Conferences and leadership teams
Speaking and facilitated sessions
Keynotes, faculty development, executive briefings, and working sessions that translate AI capability into responsible scientific practice.
NYC Science Partnership Ecosystem
In development: a cross-institutional framework connecting educators, researchers, students, and responsible-AI practitioners around applied AI literacy and AI-for-science projects.
Discuss a founding collaboration →Product system
Scientific AI products and infrastructure.
A portfolio spanning health intelligence, MCP verification, regulatory evidence, and lifecycle validation.
Flagship · Health AI
Clarity
A condition-aware intelligence system for ingredients and products. It preserves product identity, evidence, uncertainty, and health context across the checker, scanner, chat, API, and MCP.
Free public checkerPublished methodologyClarity MCP
Explore Clarity →
Trust infrastructure
MCP Queen
MCP Queen probes MCP servers and grades the evidence behind each connection. It reports reachability, metadata quality, security checks, and reproducible receipts.
Live probingDeterministic gradesPublic receipts
Visit MCP Queen →
Regulatory intelligence MCP
Constat
An MCP for source-linked FDA and CMS intelligence. Its 13 public tools support predicate research, device evidence review, and regulatory monitoring.
Visit Constat MCP →Agent access
Clarity MCP
A 12-tool MCP that gives agents access to Clarity's product, ingredient, comparison, evidence, and condition-aware safety intelligence. Responses use explicit schemas and provenance.
Connect to Clarity MCP →Validation method
RIGOR
A lifecycle validation method for high-stakes AI. It links requirements, implementation, governance, operational evidence, and runtime monitoring.
See the method →Selected work
From research question to deployed system.
I connect evidence, product design, and operational controls around decisions that carry real consequences.
Clarity: from evidence records to condition-aware decisions
I designed the product strategy and shared data contracts behind Clarity's checker, scanner, chat, API, and MCP. The system includes ambiguity handling, citation controls, and release gates across more than four million scannable products.
Read the methodology →MCP Queen: from registry to verifiable trust layer
I reframed MCP discovery as a verification problem. MCP Queen tests server reachability, applies deterministic criteria, records evidence, and monitors change.
Inspect the registry →Tire intelligence: field workflow and vision-model evaluation
I built a field inspection workflow and scanner evaluated on 203 vehicles, then published a dual-VLM consensus study with an explicit cohort, method, and scope.
View the technical publication →
Academic research
Chemistry-aware validation for AI-predicted protein structures.
At Yeshiva University, I lead a research program that combines cross-seed reproducibility, interface energetics, metal-site plausibility, and benchmarking against experimental homologs and physics-based models.
Protein-interface validationCross-seed reproducibility, interface energetics, assembly state, and controls.
Metalloenzyme systemsTYR–TYRP assemblies, human diamine oxidase, metal cofactors, and catalytic mechanism.
AI literacy in scienceTraining students and faculty to inspect model outputs, assumptions, sources, and failure modes.
AI-for-science infrastructureA supervised 25-seat Claude Team for Scientists environment and an evidence-audited Research Cockpit.
Résumé library
Explore my work.
Three tailored résumés for different kinds of work: building and implementing AI, developing research and institutional partnerships, and validating scientific or high-stakes AI systems.
AI Product, Implementation & Consulting
For product, consulting, and implementation work: workflow discovery, build/buy/automate decisions, AI products and automations, technical delivery, adoption, training, and responsible implementation.
Download PDF →Academic & Research Partnerships
For universities, research organizations, scientific programs, and frontier-AI partnerships: research communities, pilots, institutional adoption, faculty enablement, program design, and external partnerships.
Download PDF →Scientific AI, Validation & Trust
For scientific and high-stakes AI: validation, evidence architecture, provenance, failure-mode analysis, human review, lifecycle evaluation, monitoring, and chemistry-aware model assessment.
Download PDF →Work together
Build the system to withstand scrutiny.
Available for AI-literacy workshops, AI-for-science strategy, scientific AI advisory work, speaking, and research or institutional partnerships.