I build practical artificial intelligence tools for fundraising, grant insights, compliance, and digital health. My portfolio is proof that the people closest to the problem can turn judgment into a working prototype, with AI.

Fundraising and Grant Intelligence

• Funder Finder
  Turns a focus area or proposal draft into a linked set of federal and foundation opportunities, with fit signals instead of a raw search dump.
• Grant Fit Auditor
  Helps an NGO decide when not to apply by testing a grant opportunity against mission fit, evidence fit, and likely proposal burden.
• Grant Guardian Analyzer
  Reviews nonprofit financial risk signals so program and fundraising teams can ask better questions before a grant moves forward.
• NIH Subaward Checker
  Converts a narrow NIH policy notice into a practical compliance check for organizations managing subaward risk.

Strategy and Public-Interest Prototypes

• Claude Skills Creator
  Helps nonprofit teams turn repeatable expertise into structured AI workflows instead of one-off prompt experiments.
• Payer Contract Simulator
  Models how AI-assisted goal setting can change health-contract negotiations and make assumptions visible before a team commits.
• Senate Testimony Strategy
  Helps people preparing public testimony clarify the claim, audience, evidence, and likely counterargument before they speak.
• Dementia Care Billing Guide
  Translates billing complexity into a more usable decision aid for clinicians and caregivers working through dementia care options.

Digital Health

• First Signs Health
  This is the build I care about most personally. It turns published cognitive screening protocols into a browser-based, family-usable dementia screening workflow that produces a clinician-ready handoff document. It does not diagnose. It helps a family walk into a medical appointment with better information and a clearer next step.

How I Build

Built by User is my build philosophy. Software no longer requires a six-month procurement cycle before anyone tests a core idea. A domain expert can now prototype the useful 20 percent in days, then bring in engineering judgment where the work touches sensitive data, production systems, or consequential decisions.

I start with a concrete decision that wastes time or money today: which funder to pursue, whether a proposal is worth writing, what a compliance notice actually requires, or what evidence a clinician needs. I build the smallest useful tool around that decision, keep links to source material visible, and separate prototype value from production readiness.

That last boundary is the most important one. AI coding agents make software cheap to start. They do not make governance, maintenance, security, or accountability optional. My portfolio is proof of speed, but the standard is usefulness under pressure.

Why I Build

AI changes how I work. I use it to improve funder research, pressure-test proposal strategy, compare opportunities against organizational fit, and reduce the low-value labor that crowds out relationship-building. AI can sharpen the work. It does not own the relationship, replace judgment, or write the story a funder needs to believe.

That distinction matters.

We do not need more AI theater. We need practical tools that help teams decide which opportunities to pursue, which proposals are weak, where compliance risk is hiding, and when a tempting grant is a distraction.

That is why my current portfolio is focused on AI-assisted fundraising, grant intelligence, proposal discipline, and responsible implementation.