Problem Statement
Cleanups and relief drives live in scattered GCs; organizers don’t know who will come, volunteers don’t know what’s legit, and attendance is paper that gets wet. National volunteer platforms harvest data and ignore small chapters. SK and parish youth need something they control.
Proposed Solution
Chapters post needs (“10 repackers Sat 8AM, bring own tumbler”). Volunteers set skills/availability once on-device; a local ranker suggests best fits. Signup is one tap; check-in is offline QR scanned by the organizer’s phone. Chapter data exports as a static file the org keeps — no central database to leak.
Target Market
- Primary users: SK chapters, parish youth, school clubs, neighborhood associations.
- Deployers: Youth coordinators and barangay secretaries.
How AI Is Used
- On-device fit ranker: Matches skills, distance band, and past reliability without profiling server.
- Shift-note writer: Drafts Tagalog reminders and thank-you posts from attendance.
- Why AI: Simple lists overwhelm; ranked fits raise show-up rates.
Independent Deployment Angle
- Chapter-owned files, no platform account, no carrier, no venue, no headset. Any org can fork.
- Works offline at the venue; syncs when someone gets signal.
- No ads, no data resale by design.
Demo Scenario (3 minutes for judges)
- Post a mock coastal cleanup needing 10 volunteers.
- Three volunteer profiles get ranked fits on-device.
- One-tap signup, then offline QR check-in at the “venue” table.
- Organizer exports the chapter file; show it opens as a static page.
- Close: “Ang chapter ang may-ari ng datos.”
30-Hour Build Plan
| Hours | Task | Role |
|---|---|---|
| 0–3 | Interview 2 youth orgs (mock), define shift schema | All |
| 3–9 | SQLite + QR check-in + export | Backend |
| 3–12 | Ranker + note-writer prompts | AI lead |
| 10–20 | Chapter + volunteer UI | Frontend |
| 20–26 | Offline check-in drill, usability pass | All |
| 26–30 | Pitch, disclosure | PM / Pitch |
Suggested stack: Flutter + SQLite, on-device match ranker, QR check-in offline. Public data / APIs: None; synthetic volunteer profiles.
Risks & Privacy Notes
- Safety: Public events show meeting point only after signup; minors need guardian consent noted in-app.
- Privacy: Minimal data (nickname + contact with consent), chapter-held, deletable. Demo profiles fictional; no real contacts into AI tools.
- No-show risk: Reliability score is advisory and resettable, never a blacklist.
AI Use Disclosure (draft)
Uses a small on-device ranker and LM for shift notes. AI coding assistants helped with QR code. All demo volunteers are fictional and human-reviewed.
Rubric Scoring
| Criterion | Weight | Score (1–5) | Why |
|---|---|---|---|
| Innovation & creativity | 25% | 3 | Matchers exist; chapter-owned offline twist matters |
| Problem–solution fit | 25% | 4 | Fits scattered-GC chaos |
| AI application & value | 20% | 3 | Light ranking + notes |
| Feasibility | 15% | 5 | Very buildable |
| Impact & scalability | 15% | 4 | Every youth org can adopt |
| Weighted total | 3.90 |