Problem Statement
Heat now suspends classes as often as floods, but decisions are late-night guesses. Principals lack heat-index-to-classroom translation: 38°C in a concrete room with 60 kids is different from 38°C under trees. Parents learn at 5AM; kids faint by 10AM.
Proposed Solution
Enter school + classroom type: HeatClass pulls heat index, adjusts for room profile, and outputs “SHORTEN to 10AM + 2L water” or “SUSPEND afternoon Grade 4-6” with a parent SMS draft and makeup-class suggestion. History shows which schools overheat yearly for DepEd planning.
Target Market
- Primary users: Principals, parents, school DRRM in NCR, Central Luzon, Davao.
- B2G: DepEd divisions, LGU suspension deciders.
How AI Is Used
- Room adjuster: Small model maps heat index + room factors to risk band.
- Advisory writer: LLM drafts Tagalog parent messages without panic.
PLDT / Smart / ePLDT / Rokid Angle
- Smart: Early-morning SMS blasts to parents.
- ePLDT: Hosts heat history for divisions.
Demo Scenario (3 minutes for judges)
- Pick mock yero-room school at 41°C; recommendation: suspend afternoon.
- Parent SMS generates instantly.
- Show tree-shaded school at same temp: shorten only.
- History view flags yearly hot schools.
- Close: “Hindi hula ang suspension.”
30-Hour Build Plan
| Hours | Task | Role |
|---|---|---|
| 0–3 | PAGASA heat samples + room types | All |
| 3–10 | Risk model + writer | AI lead |
| 3–10 | SMS + history | Backend |
| 10–20 | Principal UI | Frontend |
| 20–26 | Teacher review | All |
| 26–30 | Pitch, disclosure | PM / Pitch |
Suggested stack: Next.js, FastAPI, heat-index ingester, SMS gateway. Public data / APIs: PAGASA heat index, DepEd suspension guides.
Risks & Privacy Notes
- Safety: Advisory only, defers to DepEd/LGU orders. Demo schools fictional; no pupil data into AI tools.
- IP: Public guidance paraphrased with sources.
AI Use Disclosure (draft)
Uses a small risk model plus LLM advisories. Coding assistants helped with UI. All demo advisories human-checked.
Rubric Scoring
| Criterion | Weight | Score (1–5) | Why |
|---|---|---|---|
| Innovation & creativity | 25% | 4 | Heat-to-classroom translator is timely |
| Problem–solution fit | 25% | 4 | Yearly heat breaks |
| AI application & value | 20% | 3 | Modest but apt |
| Feasibility | 15% | 5 | Very buildable |
| Impact & scalability | 15% | 4 | Every division |
| Weighted total | 4.10 |