📌 Current snapshot — 2026-06-24

Live

• 🛗 App (demo): https://elevator.dsaavedra.dev — AI-assisted elevator maintenance dashboard (risk-prioritised fleet, unit detail, post-visit report).
• 🌐 Portfolio: https://dsaavedra.dev — personal project index landing page.

Status

• 🟢 ML Capstone — Course 2 (CRISP-DM): Done
• 🟢 ML Capstone — Course 3 (Human Factors): Done
• 🟢 Technical PoC — Phase 1 (prototype): Done
• 🔵 Technical PoC — Phase 2: In progress — the M1–M4 milestones below are its scope.

Milestones — Phase 2

• 🔵 M1 — Dataset & Model — in progress (dataset research underway; model training, prediction pre-calculation and integration still pending); the demo fleet currently runs on simulated failure-risk scores.
• ✅ M2 — CLAUDE.md & Specs — agentic Spec-Driven workflow (OpenSpec) established.
• ✅ M3 — AWS Deployment — EC2 + HTTPS, plus a GitHub → AWS CI/CD pipeline (push to main auto-deploys via OIDC + SSM, no SSH).
• ✅ M4a — Pre-visit briefing (voice out) — on-demand briefing generated with Amazon Bedrock and read aloud via the Web Speech API, with a deterministic fallback.
• 🔵 M4b — Post-visit report (voice in) — next: record audio → Whisper transcription → pre-fill the report form.

Recently shipped

• GitHub → AWS deploy pipeline (OIDC + SSM Run Command, no stored credentials).
• Pre-visit voice briefing (Amazon Bedrock / Nova)

Next up

• M1 — gradually replace the static (simulated) risk scores with a trained ML model (pre-calculated predictions).