AI / POC Lab
Not Just Aware of AI. Using It.
This section documents what I've actually built, working systems applied to real problems. Not demos for the sake of demos. Each project started with a genuine need, got built across multiple sessions, and is either in active use or in progress. The stack varies. The approach is the same: figure out what AI can actually do by building something that has to work.
Active projects
A job search generates a lot of moving parts fast. Dozens of open applications across LinkedIn, Indeed, and company career sites. Recruiter messages, networking contacts, referral threads. Follow-up deadlines that shift daily. Screening criteria that vary by role, industry, and comp band. Without a system holding all of this together, context gets lost between sessions. You re-screen roles you already rejected. You miss follow-ups. You waste time on roles that don't fit. The search slows down at exactly the point it needs to speed up.
Job search inboxes fill up fast. LinkedIn alerts, Indeed alerts, recruiter emails, ATS status updates, rejection notices. They pile up daily. Processing them manually means opening each email, checking if the role fits, checking if you already applied, checking if it's expired, checking the salary range, then deciding whether to act. Miss a day and good roles age out. Miss a follow-up and a warm lead goes cold. The triage work is repetitive, time-sensitive, and easy to fall behind on.
Most families navigate college decisions with spreadsheets, gut feel, and competing opinions. This tool forces clarity by weighting every factor that matters, scoring every school, and updating rankings in real time as aid letters arrive and campus visits happen.
Discount retail has no differentiation. This platform ties every purchase to a transparent, publicly auditable giving formula. Customers see exactly how their savings translate to donations for underserved NYC school districts.
Coming soon