AI workforce management for hotels on protel.
HotelCadence is a workforce management platform for hotels: it reads the reservation data already in protel (read-only, cloud via API or on-premise via scheduled exports) and turns it into hourly demand forecasts per department and auto-drafted rosters your managers approve. Hotels cut 6–12% of labor cost without cutting guest service — and nothing writes back into protel.
Calculate your labor savings →Book a demo with your own protel data
protel by Planet · vendor website: weareplanet.com ↗
Osaka, 220 rooms: the 15:00 check-in wall was in protel all along
With check-in at 15:00 sharp, arrivals do not curve, they pile. This chain property rostered the desk flat at six from 10:00: the quiet morning paid for agents with nothing to process, and the 16:00 peak of eleven agents' worth of arrivals queued into the lobby. The hourly arrival counts predicting it were already in protel.
The data behind this chart
| Hour | Staff required | Flat roster | Demand-matched roster |
|---|---|---|---|
| 10:00 | 2 | 6 | 2 |
| 12:00 | 3 | 6 | 3 |
| 14:00 | 4 | 6 | 4 |
| 15:00 | 9 | 6 | 9 |
| 16:00 | 11 | 6 | 11 |
| 17:00 | 10 | 6 | 10 |
| 18:00 | 8 | 6 | 8 |
| 19:00 | 7 | 6 | 7 |
| 20:00 | 5 | 6 | 5 |
| 22:00 | 3 | 6 | 3 |
Worked example, figures indicative, 220-room city property.
Put your own numbers on this → the calculator takes two minutes and needs no email — or see pricing first.
The workforce management layer on top of protel
Three modules on one read-only data feed, measured against your own baseline. Labor runs 32.4% of hotel revenue (CBRE, US benchmark); demand-matched scheduling recovers 6–12% of it.
AI demand forecasting
Arrivals, departures and covers forecast per department, per hour, from live protel data.
How forecasting works →AI staff scheduling
Draft rosters at the lowest cost that still hits your service standard; managers approve every schedule.
How scheduling works →PMS data insights
Revenue, labor cost and productivity per property on one live screen, straight from protel.
See the insights →Go live in three steps
Read-only access · counts and dates only, no guest-identifying data · revocable at any time.
Authorize read-only access
protel cloud properties authorize a read-only connection through the documented protel APIs; on-premise installations start from scheduled read-only exports. Either way it is configuration, not an interface project, and revocable at any time.
Backfill and calibrate
HotelCadence pulls up to two years of protel reservation history and calibrates hourly demand forecasts per department against your own actuals, so accuracy is proven on your data before anyone rosters against it.
Go live and measure
Forecasts refresh as pickup changes and draft rosters flag shifts that no longer match demand. Managers approve everything, and results are measured monthly against your agreed baseline.
protel integration questions, answered
How long does a protel integration take?
Cloud properties authorize read-only API access and connect first; on-premise installations start from scheduled exports, scoped in the integration audit. Backfill and forecast calibration run in parallel, and integration is included in the 90-day pilot (from US$7,500).
We run protel on-premise, does that work?
Yes. On-premise protel installations connect via scheduled read-only exports of reservations, arrivals, departures and occupancy, and switch to a direct feed where the installation supports it. Nothing is installed on your front-desk machines beyond the export task.
Our check-in time concentrates arrivals into two hours, can a roster follow that?
That concentration is the reason to roster hourly. A fixed check-in time turns the arrival curve into a wall, so a flat roster is simultaneously overstaffed at 11:00 and drowned at 16:00. Hourly forecasts from protel data staff the wall itself, including split and staggered shifts where your rules allow them.
Does HotelCadence write anything back into protel?
No. The connection is read-only and nothing is written back, rates, reservations and guest profiles in protel are never touched. Forecasts and draft rosters live in HotelCadence, where managers review and approve them.
Where does our data live, and what about guest privacy?
HotelCadence needs counts, dates, rates and segments, not guest-identifying data. Hosting is in-region, with Singapore as the default APAC residency and options consistent with Japan’s APPI for Japanese portfolios.
Part of our portfolio runs OPERA Cloud or Mews, can one rollout cover both?
Yes. protel properties connect via their read-only feed, OPERA Cloud via OHIP, Mews and Cloudbeds via their own APIs, and the whole portfolio rolls up into one view with identical per-department, per-hour forecasts and one baseline measurement method.
Calculate your labor savings →Book a demo with your own protel data
The calculator takes 2 minutes, no email needed · the demo runs on your live arrival curve · no obligation.