Portfolio
Projects & Applied Work
We build in the open and ship working AI. A selection of open-source projects, applied research, and the engagements we deliver across industries.
AI Security & Agentic Systems
Agentic Red Team
Tooling to adversarially probe and test AI agents for security weaknesses, prompt-injection, and unsafe behavior.
Agentic Blue Team
Defensive monitoring, guardrails, and detection for agentic AI systems in production.
MCP & Enterprise Software
ServiceNow MCP Server
A Model Context Protocol server connecting Claude and other AI clients to ServiceNow (enterprise ITSM) via its Table and REST APIs. Our security-hardened, feature-consolidated fork registers 216+ tools with 919 passing tests and mitigated security findings.
Bioinformatics, Drug Discovery & Drug Development
Peer-Reviewed Publication · Scientific Reports (Nature Portfolio)
RAG-based architectures for drug side effect retrieval using compact LLMs
Shad Nygren (lead author), Omer Erdogan, Pinar Avci, Andre Daniels, Reza Rassool, Afshin Beheshti & Diego Galeano. Scientific Reports 16, 12754 (2026). Published 9 March 2026.
The authors are affiliated with institutions including the Broad Institute of MIT and Harvard, Harvard Medical School and Massachusetts General Hospital (Wellman Center for Photomedicine), the University of Pittsburgh, Koç University (KUIS AI Center), the Universidad Nacional de Asunción, and Kwaai.
We evaluate retrieval-augmented architectures that inject curated knowledge from the Side Effect Resource (SIDER) into compact LLM workflows for answering drug-side-effect questions. The graph-based approach (GraphRAG) achieved near-perfect accuracy—returning exact results with 100% precision, recall, and F1 on reverse queries—at substantially lower latency than a text-based baseline.
Protenix — Protein Structure Prediction
Work with a trainable PyTorch reproduction of AlphaFold 3 for protein structure prediction. Our fork adds containerized Docker builds, automated security scanning, and CI test coverage—production hardening for drug-discovery workloads.
RAG for Drug Side-Effect Retrieval
Retrieval-augmented architectures for surfacing drug side effects with LLMs—applied biotech research for drug development.
RAG & LLM Applications
RAG Demo on Azure
A retrieval-augmented generation demo deployed on Azure Static Web Apps.
Data, Compliance & Infrastructure
Data Sovereignty Layer
A layer that enforces data privacy and compliance with regulatory requirements.
Consulting Engagements
Beyond open source, we deliver hands-on consulting across our focus industries—biotech & drug discovery, mining & geology, real estate, and robotics—plus AEO & GEO optimization. Every engagement ships working deliverables: custom code, trained models, automation, and secure cloud infrastructure.
Client Reviews & Recommendations
Verified client reviews and professional recommendations are available on our Upwork and LinkedIn profiles.