0 to 45%
City Blue Hotels
Direct revenue in 6 months.
Whizz AI
AI that detects, then acts inside your rules
On your data. In your systems. With the evidence kept.
AI-powered means different things. Here is what it means for us: it detects on the hotel’s own data, acts only in ways the hotel has configured, writes the result back into the systems the hotel already runs, and keeps a record of what it saw and did.
app.bookingwhizz.com
BH
BookingWhizz Hotel
Loyalty results
AI surfaces
0
all live today
Price checks
0
rate, geo, device, member fare
Price snapshots
0
kept this week by PriceMatch
Rules invented
0
every response is yours
Whizz AI
Detected: Lower served price for Lakeside’s Deluxe Room on mobile, member fare, same dates
Activated: Configured response applied, snapshot kept, guest booked direct
Detected and answered in under 30 seconds
Our position on AI
AI that detects on the hotel’s own data, acts inside the hotel’s rules, writes back to the systems the hotel already runs, and keeps the evidence.
Five steps, the same every time. When a guest accepts an upgrade, WhizzCRM updates the reservation in Opera Cloud through OHIP. On a PMS connected one way, the request goes to your team to fulfil, and we say so.
Step 1
Read
The hotel’s own PMS, engine, loyalty and CRM data, and the live price the guest is shown on Booking.com.
- Guest profileGold, 4 stays
- Rate planExecutive Suite
- Booking.com$186 on mobile
Step 2
Decide
A score or a detection, handed to the rule the hotel configured. The rule decides.
Upgrade likelihood 78%
Riverside rule: offer above 70%
Rule met. Proposed action.
Step 3
Act
The action the rule allows: an offer, a matched rate, a draft, a message on the channel the hotel chose.
Executive Suite
Upgrade with points, pre-arrival
Step 4
Write back
The result lands in the systems the hotel already runs: engine, loyalty, CRM, CMS, and the PMS where connected.
- WhizzCRM message sent 10:02
- Reservation updated in the PMS 10:03
- Loyalty points reserved
Step 5
Keep the evidence
Every action carries what was detected, the rule, who approved it and what was written back.
10:02:14 · Detected · 78%
10:02:15 · Rule R-07 · offer sent
10:03:41 · Accepted · written back
Where it runs
Four surfaces. All built, all live.
AI is not a product we sell on its own. It runs inside four places in the platform. For each one: what it detects, what the hotel’s rule does about it, and what it needs to be connected to.
Live on all major OTAsBooking engine only
PriceMatch
Booking EngineDetects the price the guest is actually shown, on rate, geo, device and member fare, live. Applies the response the hotel configured. Keeps a snapshot.
Detected
Lower served price found
A guest on a phone in Germany is being shown Lakeside’s Deluxe Room for the same dates at a lower price on Booking.com than on Lakeside’s own site.
Activated
Configured response applied
PriceMatch applied the response Lakeside configured for a mobile, member-fare mismatch, and kept a snapshot of both prices. The guest booked direct.
Detected and answered in under 30 seconds
WhizzCRM and WhizzLoyaltyTwo-way PMS for reservation write-back
Whizz AI recommendations
WhizzCRM and Guest JourneyUpgrade likelihood, tier-due nudges and lapsed-guest segments, scored on the property’s own history. Each one is acted on by a rule the hotel configured in WhizzCRM and the guest journey.
Detected
Upgrade likelihood
A repeat guest at Riverside, Gold member, arrives tomorrow. 78% likelihood of accepting a suite upgrade, based on four previous stays.
Activated
Pre-arrival offer sent by Riverside’s rule
Riverside’s pre-arrival rule sends the upgrade offer to guests above its threshold, on the channel Riverside chose. Accepted within 47 seconds.
Executive Suite taken, one message
AI build in every WhizzSiteWriting assistant in WhizzSite Group
WhizzSite
AI build and the WhizzSite Group writing assistantBuilds the hotel’s site from what it finds about the property. In WhizzSite Group, the writing assistant drafts from the property’s facts for the manager to approve.
Detected
Thin page copy
Quay’s Garden Room page has a 40-word description, no SEO title and no meta description. Six of its eight photos have no alt text.
Activated
Drafts written from the facts
The writing assistant drafted a description from the room’s recorded facts, an SEO title and meta, and alt text from each image. Quay’s manager approved and published in the CMS.
Description, title, meta and 6 alt texts, one review
Inside WhizzCRMReview sources the hotel connects
Review replies
WhizzCRMReads new reviews, drafts a reply in the hotel’s own tone, and tells the manager what the guest said and how they felt.
Detected
Three-star review
A new three-star review for Riverside mentions a slow check-in and a room that was not ready on arrival.
Activated
Reply drafted, manager notified
A reply in Riverside’s tone was ready in 4 minutes. The manager was notified with the guest’s details and the sentiment, and decides what is posted.
Ready in 4 minutes
The evidence
Every action carries what was detected, the rule, who approved it and what was written back.
The owner can audit any day. One screen, on BookingWhizz Riverside.
BookingWhizz Riverside
Whizz AI · Evidence · Tuesday 12 May
5 events · 4 activated · 1 proposed
09:14:02
PriceMatch
Activated- Detected
- Deluxe Room, 12 to 14 May. Booking.com $186 on a phone in Germany, direct $192.
- Proposed
- Match the public rate at $186 and show the member fare with 3,720 points.
- Approved by
- Rule R-04, configured by Riverside. Snapshot of both prices kept.
- Written back
- Booking engine, 09:14:03. Guest booked direct 09:21.
10:02:14
Whizz AI recommendation
Activated- Detected
- Gold member arriving tomorrow. Upgrade likelihood 78% on four previous stays.
- Proposed
- Pre-arrival Executive Suite offer, paid with points.
- Approved by
- Rule R-07, pre-arrival, threshold 70%.
- Written back
- WhizzCRM message 10:02. Accepted 10:03. Reservation updated in the PMS 10:03.
11:40:55
Review reply
Activated- Detected
- New three-star review: slow check-in, room not ready on arrival.
- Proposed
- Reply drafted in Riverside’s tone, with the guest’s details and the sentiment.
- Approved by
- Front office manager, 12:15. Two lines edited.
- Written back
- Posted to the review source, 12:16.
14:05:30
Whizz AI recommendation, Grow
Proposed action- Detected
- Visitors from google.com, 4,120 in 30 days, book at 1.0x the site average.
- Proposed
- Show the free-cancellation term on the rate page. No discount.
- Approved by
- Awaiting the revenue manager.
- Written back
- Nothing yet. Written back when approved.
15:30:08
Whizz AI recommendation
Activated- Detected
- Member reached 12 stays this year. Top tier due, with the spa benefit attached.
- Proposed
- Apply the tier and send the welcome message.
- Approved by
- Rule R-02, tier progression.
- Written back
- Loyalty programme 15:30. Welcome message through WhizzCRM 15:30.
Every row can be opened to the snapshot or the message it produced. Nothing is deleted.
Whizz AI
Whizz AI proposes, you approve
Recommendations on the hotel's own website data, ranked by bookings gained, never by conversion rate alone. Every set carries one of each play. Grow and Protect cost nothing and work on any booking engine. Rescue stays inside a rule head office set, and a person approves before anything goes live.
1Grow
Proposed actionLargest segment, converting near the site average
Detected
Visitors from google.com, 4,120 in the last 30 days, book at 1.0x the site average. The largest segment on the site.
Proposed action
Remove friction, no discount. Show the free-cancellation term on the rate page and the member voucher one step earlier.
- Cost
- No discount
- Measure
- Bookings per 1,000 visitors, before and after
- Target
- A target measured after 30 days, never a promise
Approve to publish2Protect
Proposed actionStrong segment, 1.5x the site average or better
Detected
Returning members, 640 visitors in 30 days, book at 1.8x the site average. Already the best-converting segment.
Proposed action
Recognise the member on arrival and offer the next room up with points. Never a discount.
- Cost
- None
- Measure
- Revenue per booking, repeat rate
- Target
- A target measured after 30 days, never a promise
Approve to publish3Rescue
Proposed actionWeak segment, under 0.4x the site average, with real volume
Detected
Visitors from instagram.com, 1,280 in 30 days, book at 0.3x the site average. Volume justifies a test.
Proposed action
One capped test: an extra direct discount at most the head office limit, shown to half the segment, the other half as control. Kept or killed on the result after 30 days.
- Cost
- Discount, capped by head office
- Measure
- Lift against the control group
- Target
- A target measured after 30 days, never a promise
Approve to publish
Segments below the size rule are ignored. Nothing is proposed on a sample too small to measure.
These are configured rules. Whizz AI proposes; a person approves. Nothing tunes itself.
Booking attribution is claimed only where an engine capture is in place.
Written from the facts
Every line a draft contains names the data it came from.
The guest profile, the rate plan, the review, the room record. The hotel edits, approves and publishes. Nothing publishes without the hotel.
Whizz AI recommendation
Pre-arrival upgrade offer
To Karim, Gold member, arriving tomorrow
Welcome back for your fifth stay with us.
Source: Guest profile: 4 previous stays, Gold
The Executive Suite is available for your dates, for 9,500 points.
Source: Rate plan: Executive Suite, points price, 12 to 14 May
Late checkout is included with your tier.
Source: Loyalty programme: Gold benefits
Sent by rule R-07 on the channel Riverside choseDraft
Review reply
Reply to a three-star review
Draft for the front office manager
Thank you for telling us about the wait at check-in on Saturday.
Source: Review text, 9 May
Your room should have been ready at 15:00 and it was not. That is on us.
Source: Reservation record: arrival 9 May, room ready 16:10
We would like to welcome you back with a room ready on arrival.
Source: Riverside tone settings: warm, direct, no excuses
The manager edits, approves and postsDraft
WhizzSite writing assistant
Garden Room description
Draft for the page editor
A 32 m² room with a king bed and doors onto the walled garden.
Source: Room record: 32 m², king, garden access
Breakfast is served in the orangery from 7:00 to 10:30.
Source: Property facts: breakfast hours, venue
Alt text: garden room with king bed and open doors to the lawn.
Source: Image garden-room-02.jpg
The editor edits, approves and publishes in the CMSDraft
Assistants
When the guest asks an AI assistant
More guests start a trip by asking an assistant rather than a search box. The hotel’s direct rate should be what the assistant finds.
What is true today
- 01Our own site welcomes AI crawlers by name in its robots file and publishes a machine-readable summary at
/.well-known/llms.txt. - 02The hotel websites we build are legible to the same crawlers: plain structure and real text for every room and offer.
- 03PriceMatch keeps the direct rate the one worth finding, so an assistant that reads the hotel’s own site reads the right price.
A posture, not a product. We do not sell an AI visibility service, and we do not publish a visibility score we cannot measure.
Questions owners ask
Six questions, straight answers.
Is Whizz AI a separate product?
No. It is the capability inside four surfaces the platform already runs: PriceMatch, Whizz AI recommendations in WhizzCRM, the WhizzSite writing assistant, and review replies.
Is my data safe?
SOC 2 Type II held. ISO 27001 in progress. The hotel is the controller, BookingWhizz the processor. The property’s guest, rate and booking data stays in the property’s account. It is not pooled, resold or used to train anything for another hotel.
Does the AI ever change a rate on its own?
No. PriceMatch reports the price a guest was actually shown and applies a response the hotel configured. It never sets a rate on its own, and it never tunes its own rules.
What happens when PriceMatch finds a lower price?
Live detection runs on all major OTAs. The response the hotel configured is applied: the public rate is matched, member value is carried in points and perks, and a snapshot of both prices is kept.
Who approves a review reply or a page draft?
The hotel. Drafts are written from the facts the hotel holds, and each line shows its source. The manager edits, approves and publishes. Nothing publishes without the hotel.
What does the guest see?
Only what the hotel approved: a message on a channel the hotel chose, with the offer the hotel set. No AI talks to a guest outside the hotel’s rules.
See what Whizz AI would detect at your property
WhizzAudit runs on your own numbers and shows you what the four surfaces would find and act on today.