⚡
Built with agentic AI. Development on this project runs through multi-agent Claude Code
workflows — developer → independent-reviewer cycles with evidence gates, batched into unattended runs that
execute overnight and resume from committed ledgers. How the agent system works →
The product mechanism
A host uploads walkthrough videos and PDFs once; guests then get instant, grounded answers on WhatsApp — including auto-cut video clips of the exact moment that answers their question.
Ingestion pipeline
- Walkthrough videos and house-manual PDFs land in object storage; FFmpeg extracts audio, Whisper transcribes, an LLM pass detects topics (WiFi, check-in, parking…).
- Transcript chunks are embedded into Qdrant; structured property/booking data lives in Postgres.
- Conversations map to booking, property and host, so every answer is scoped to the right apartment.
Guest conversation loop
- Messages arrive via the WhatsApp Business API; RAG retrieval runs over the property's own knowledge — answers are grounded in the host's actual walkthrough.
- When the best evidence is a video moment, FFmpeg auto-cuts a clip at the right timestamp and sends it with the reply.
- Low-confidence answers escalate to the host — the assistant's job is to handle the routine 80%, measurably.
Designed like engineering
Unit economics before product code
The core design artifact is a dataclass-driven cost model that separates one-time onboarding from monthly run-rate — and the real cost driver, narrated media (Whisper path) from silent media — fanned across portfolio sizes from 10 to 200 listings. Pricing conversations with property managers happen over a spreadsheet-grade model, not a guess.
Pilot, demo & operating model
- Pilot tiers with success metrics defined before the pilot starts: % handled without a human, escalation rate, time-to-first-reply.
- A repeatable 15-minute demo with a fixed demo-apartment fixture, so on-stage answers are deterministic; every sales-call promise becomes a tracked issue.
- A 3-person operating model (2 dev, 1 sales) and a full deployment story: Next.js + Clerk on Vercel, FastAPI workers, Stripe billing, staging-before-prod.