01
Clinical workflow
I translate clinical needs into intended users, workflow states, handoffs, escalation boundaries, and safe-stop behavior.
Clinical researcher / founder / systems builder
Dr. Manu Faujdar
My work grows out of years of experience in medical training, entrepreneurship, and technology. I move between non-invasive sensing, patient experience, privacy-aware AI, and research tools because the most interesting problems rarely stay in one field.
More about meWhat I pay attention to
02
Health-tech framing
I turn an early health-tech idea into a clearer brief: intended use, product requirements, data boundaries, risks, and the next validation gate.
03
Reliable AI
I build research prototypes for explainable routing, outbound-data inspection, deterministic testing, and consent-aware memory so decisions and failures are inspectable.
04
Research and evaluation
I turn broad translational questions into studyable designs with reference standards, confounder planning, provenance, leakage-safe validation, and claims matched to evidence.
Selected work
Open source
AI Routing Gateway
AI Routing Gateway is intended to send each query to the model or specialist workflow most likely to return a reliable answer, while keeping the routing decision explainable and testable across multiple LLMs.
Open source
AI Firewall
AI Firewall is intended to inspect outbound data before a cloud AI call and allow, redact, or block sensitive information, giving regulated teams a visible privacy control for each request.
Private work
BioVOC
BioVOC is intended to investigate whether biological volatile organic compounds found in breath can signal cancer-related activity in the body, using a non-invasive breath sample and a traceable validation pathway.
Private work
Clinical Feedback System
Clinical Feedback System is intended to collect and reward honest patient feedback, route themes to the right service owner, and support patient engagement and retention without absorbing clinical escalation. The prototype uses synthetic scenarios.
Working notes
Questions I am using to connect clinical context, evidence, and reliable systems.
Patient experience
Why do most patients leave without telling us what they really experienced?
A closer look at the silent gap between a patient visit, an honest response, and the reason someone chooses to return.
Clinical AI
When should a clinical AI system say, “not here”?
A closer look at how a safe refusal can protect a clinician’s time, a patient’s safety, and the handoff when a case exceeds the model’s intended use.
What makes a problem worth pursuing
I am most interested in the point where a clinical, technical, or social problem is still rough—where a sharper question, a testable workflow, or a well-built prototype can change what becomes possible next.
The work I return to has real stakes, incomplete evidence, or a privacy boundary that deserves to be made visible.