This page is organized like a proof system, not a flat archive. The strongest recruiter-facing work appears first, followed by supporting systems work and lighter concept studies.
Proof first
Not every page is meant to do the same job. The clearest public proof comes first, the active systems work stays visible, and lighter exploration remains accessible without crowding the main story.
These are the first pages I would want a recruiter, hiring manager, or collaborator to open.
Why it matters
The rebuild made the site faster to understand and stronger as a hiring asset.
A case study on rebuilding georgeandary.com into a clearer, proof-led portfolio.
A live private ritual tool for daily goal repetition, optional monthly planning, and quarterly reflection.
Why it matters
Live now with a daily-first ritual, optional monthly mode, browser reminders, archive review, quarterly reflection, and entity-linked goals.
A live mortgage-style intake demo that shows borrower routing, conversion flow, and team handoff.
Why it matters
It demonstrates how lead logic, borrower experience, and team handoff can work as one system.
A live rugby trainer that teaches when to keep, pass, take contact, or scan again.
Why it matters
Live now with a beginner mode, full decision mode, and a reusable training system.
These pages show process maturity, workflow thinking, and active build motion without all competing for the same top-level emphasis.
A public-safe status layer that shows active work without exposing private detail.
Why it matters
It makes live work easier to see, follow, and trust from the portfolio.
A workflow system that keeps research, proof checks, implementation, and QA connected across threads.
Why it matters
It turns scattered thread work into reusable docs, handoffs, and repeatable execution.
A selected-output system that turns strong thread work into briefs, packs, and scoped artifacts worth keeping.
Why it matters
It makes strong thread work reusable instead of leaving it buried in chat history.
A local Windows dictation build with hotkeys, private transcription, and a paste-into-any-app workflow.
Why it matters
The current build already handles hotkeys, local transcription, paste, phrase hints, and saved settings.
GitHub tracked privately: speakfree
A mobile prototype for recovering messy voice notes through local audio, AI cleanup, and next-day review.
Why it matters
The current prototype already records locally, preserves session history, supports playback, cleanup review, tags, search, reminders, and simple resurfacing logic.
These pages stay in the portfolio because they show product judgment, trust-model thinking, or research framing, even when the public artifact is intentionally lighter.
A private research concept for turning messy tax questions into a more structured review workflow without pretending the model should act as a tax advisor.
Why it matters
It became a strong concept study in how high-risk AI tools should separate synthesis from decision authority, preserve uncertainty, and force human review before anything becomes actionable.
