Skip to main content
The Smart Scheduling Engine analyzes appointment patterns, predicts no-shows, optimizes room utilization, and automatically fills cancellations through intelligent waitlist management.

​
Overview

Etienne’s scheduling intelligence works behind the scenes to maximize revenue per provider hour while improving the client experience.

Utilization Boost

Average 18.5% increase in room utilization after AI implementation

No-Show Reduction

57% reduction in no-show rates through predictive intervention

​
Key Metrics

​
Utilization Rate

Definition: 
(Booked appointment hours / Total available provider hours) × 100
Example calculation:
  • 3 providers × 8 hours/day × 5 days = 120 total hours
  • 98 hours of booked appointments = 82% utilization
Industry benchmarks:
  • Below 70%: Underutilized (revenue opportunity)
  • 70-85%: Healthy range
  • Above 85%: Near capacity (consider adding providers/rooms)
What the metric shows you:
  • Current: Average utilization over last 30 days
  • Trend: % change vs. previous 30-day period
  • Location filter: Compare utilization across centers
Utilization rates naturally vary by day of week. Saturdays typically run 15-20% higher than Mondays. Use the trend line to spot patterns.

​
No-Show Rate

Definition: 
(Appointments marked no-show / Total confirmed appointments) × 100
Industry average: 15-25% without intervention
With Etienne AI: 4-8% average Revenue impact: A spa with 500 appointments/month at $400 average:
  • 20% no-show rate = 100 no-shows = $40,000 lost revenue/month
  • 5% no-show rate = 25 no-shows = $10,000 lost revenue/month
  • Savings: $30,000/month
Trend to watch: Negative trend percentage (green, down arrow) indicates improvement. You want this number going down.

​
AI-Booked Appointments

Count of appointments booked entirely by AI without staff involvement. Breakdown by source:
  • After-hours calls and texts
  • Web chat bookings
  • Social media DM bookings
  • Automated rebooking campaigns
  • Waitlist auto-fill
Typical range: 35-45% of total bookings Why it matters: Each AI booking frees staff time for higher-value activities like consultations and relationship building.

​
Revenue per Appointment

Calculation: 
Total appointment revenue / Number of completed appointments
Factors that increase this metric:
  • Service mix (higher-value treatments)
  • Effective upselling (add-ons)
  • Package sales
  • Longer appointment durations
How AI helps:
  • Suggests relevant add-ons during booking
  • Identifies upsell opportunities in conversation
  • Books package-deal combinations
Example: Without AI: 385averageWithAI:385 average With AI: 420 average (+8.2%)
On 500 monthly appointments: +$17,500/month revenue

​
No-Show Prediction & Prevention

The No-Show Predictor AI agent analyzes 15+ factors to calculate risk scores for every confirmed appointment.

​
Risk Factors Analyzed

  • Previous no-show rate for this client
  • Days since last visit (longer gap = higher risk)
  • Lifetime visit count (new clients higher risk)
  • Payment method on file (card vs. invoice)
  • Average days between booking and appointment

​
Risk Levels

Low Risk

0-30% probabilityNo intervention needed beyond standard confirmation

Medium Risk

31-65% probabilitySend additional reminder 2 hours before appointment

High Risk

66-100% probabilityMultiple touchpoints:
  • 24-hour reminder
  • 2-hour reminder
  • Personal call if no confirmation

​
Prevention Actions

When high-risk appointments are detected: Automated interventions:
  1. 24-hour reminder sent via client’s preferred channel
  2. 2-hour warning with one-click confirm/cancel
  3. If no response: Waitlist notified of potential opening
  4. 30 minutes before: Final text reminder
Example prevention flow: 
Day before, 10 AM:
[AI] Hi Emma, friendly reminder — your Hydrafacial is tomorrow 
     at 9:30 AM at Williamsburg. Reply YES to confirm or CANCEL 
     to reschedule.
     
[No response after 12 hours]

Appointment day, 7:30 AM:
[AI] Your Hydrafacial starts in 2 hours at Williamsburg. 
     Still coming? Reply YES or CANCEL.
     
[Client - 7:45 AM] Yes running a little late though, maybe 10 min

[AI] No problem! We will have everything ready. See you soon!

✅ No-show prevented
Success rate: 73% of high-risk appointments are confirmed through this intervention sequence.

​
No-Show Rate Trend Chart

30-day no-show rate trend
Line chart showing daily no-show rate over 30 days. What to look for:
  • Downward trend: AI interventions working
  • Spikes: Investigate cause (weather, specific provider, service type)
  • Day-of-week patterns: Mondays and Fridays typically higher
Typical progression after AI implementation:
  • Week 1-2: 12-15% (baseline)
  • Week 3-4: 8-10% (AI learning)
  • Month 2+: 4-6% (steady state)

​
Utilization Rate Trend

30-day utilization trend
Line chart showing provider room utilization over time. What drives utilization improvements:
  • Fewer no-shows (slots get used as booked)
  • Waitlist auto-fill (cancellations filled immediately)
  • Optimized scheduling (AI books slots that would stay empty)
  • After-hours bookings (inventory that was previously unavailable)
Example: SoHo location with 6 rooms:
  • Before AI: 74% average utilization
  • After 3 months: 86% utilization
  • Additional revenue: 12% × 85Kmonthlycapacity=+85K monthly capacity = +10,200/month

​
High No-Show Risk Appointments

Real-time list of upcoming appointments flagged as high-risk. Display format: 
⚠️ Sarah Chen
Hydrafacial • Mar 15 at 10:00 AM
[Send Reminder] button
Information shown:
  • Client name
  • Service and provider
  • Date and time
  • Risk level (color-coded)
  • Action button
Staff actions:
  • Send Reminder: Triggers immediate SMS reminder
  • Call Client: Opens dialer with client number
  • View History: See client’s past appointment attendance
If the high-risk list consistently shows >20 appointments, consider adjusting your booking policies (e.g., require credit card for first-time clients).

​
Waitlist Management

Intelligent waitlist automatically fills cancellations and no-shows.

​
How It Works

Client adds themselves to waitlist:
  • Through website
  • Via SMS/chat conversation
  • Staff can add manually
When a slot opens:
  1. AI identifies opening (cancellation, no-show, new availability)
  2. Matches waitlist clients by:
    • Requested service
    • Preferred provider (if specified)
    • Location preference
    • Available dates/times
  3. Sends notification to first match: 
    [AI] Hi Nicole! A Botox slot just opened up tomorrow at 11 AM 
     at White Plains. You are first on the waitlist. Want it?
  4. If accepted: Books appointment automatically
  5. If declined or no response in 10 min: Offers to next person
Conversion rate: 68% of waitlist notifications convert to bookings Revenue recovery: Typical med spa with 30 cancellations/month:
  • 30 slots × 68% fill rate = 20 appointments saved
  • 20 × 400average=400 average = 8,000 recovered revenue/month

​
Waitlist Priorities

  1. VIP clients (highest spend, longest tenure)
  2. Long waitlist time (first-come, first-served among same tier)
  3. High-value services (Body Contouring prioritized over Botox)
  4. Perfect match (exact service, provider, and time requested)

​
Schedule Optimization

The Schedule Analyst AI continuously looks for optimization opportunities:

​
Slot Consolidation

Problem: Two 30-minute Botox appointments with a 30-minute gap between them
Solution: AI suggests moving one appointment to fill the gap
Result: Opens a new 60-minute slot for higher-value service (Hydrafacial, Filler) Revenue impact example:
  • Before: 2 × Botox (450each)=450 each) = 900
  • After: 2 × Botox + 1 × Hydrafacial (250)=250) = 1,150
  • Gain: +$250 per optimization

​
Provider Balancing

Problem: Provider A at 92% utilization, Provider B at 68%
Solution: AI preferentially books new appointments with Provider B
Result: Balanced workload, better client experience (shorter waits)

​
Service Mix Optimization

Problem: All high-value slots filled with low-value services
Solution: AI reserves prime times (Sat 10 AM-2 PM) for services >$500
Result: Revenue per hour increases Example rule: 
Saturday 10 AM - 2 PM slots:
- Priority 1: Body Contouring ($1,200)
- Priority 2: Dermal Filler ($850)
- Priority 3: Botox ($450)
- Priority 4: Other services
Optimization suggestions appear in the dashboard AI Opportunities panel. Staff can accept or decline each suggestion.

​
Rebooking Automation

AI tracks treatment cycles and proactively reaches out for rebooking.

​
Treatment Schedules

ServiceRecommended Interval
Botox3-4 months
Dermal Filler6-9 months
Hydrafacial4-6 weeks
Laser Hair Removal4-6 weeks
Chemical Peel4-8 weeks

​
Automated Outreach

Example: Botox rebooking 
Last visit: December 15
Today: March 10 (85 days later)
Ideal rebook window: 90-120 days

[AI - Day 85] Hi Angela! It has been almost 3 months since your 
              last Botox session. Ready for the next one?
              
[Client] Yes! Friday works best.

[AI] Friday at 1 PM at Williamsburg. See you then!
Rebooking metrics:
  • Outreach rate: % of past clients contacted at right time
  • Response rate: % who reply to rebooking message
  • Conversion rate: % who actually book
Typical performance:
  • 78% response rate
  • 64% conversion rate
  • 15-25% revenue attributed to automated rebooking

​
AI Scheduling Agents

Three specialized agents power the scheduling engine:

​
Schedule Analyst

Status: ● Online
Tasks Handled: 1,893 Responsibilities:
  • Analyzes utilization patterns
  • Identifies optimization opportunities
  • Manages waitlist matching
  • Coordinates multi-appointment bookings

​
No-Show Predictor

Status: ● Online
Tasks Handled: 647 Responsibilities:
  • Calculates risk scores for all appointments
  • Triggers preventive reminders
  • Tracks intervention success rates
  • Updates prediction model based on outcomes

​
Demand Forecaster

Status: ◐ Idle
Tasks Handled: 89 Responsibilities:
  • Predicts demand by day/time/service
  • Recommends optimal staffing levels
  • Identifies under/over-capacity periods
  • Suggests pricing adjustments for demand shaping
Demand Forecaster runs weekly analyses rather than real-time processing, which is why it often shows “Idle” status.

​
Staff Scheduling View

​
Today’s Timeline

Chronological view of your appointments for the current day: 
09:00  Sarah Johnson          Botox · Dr. Chen           $450
       ⚠️ High Risk
       
10:30  Maria Lopez            Hydrafacial · PA Johnson   $250

13:00  [Open Slot]

14:00  Jennifer Kim           Dermal Filler · Dr. Chen   $850

16:00  Amanda White           Laser Hair · NP Williams   $350
       Running 10min late (confirmed)
Visual indicators:
  • ⚠️ High no-show risk
  • 🔵 Client confirmed
  • 🟡 No confirmation yet
  • 🟢 Checked in
  • ⏰ Running late (with estimate)

​
Quick Actions

  • Send Reminder: One-click SMS reminder
  • Call Client: Click-to-dial
  • Reschedule: Drag-and-drop to new slot
  • Add Notes: Attach notes visible to provider

​
Best Practices

Start your day by:
  1. Checking the High No-Show Risk list
  2. Sending personal reminders to top 3-5 risks
  3. Notifying waitlist for any likely no-shows
This 10-minute routine typically saves 2-3 appointments per day.
When AI suggests filling a slot from the waitlist:
  • Client is waiting for your confirmation
  • They’ve already said yes to the notification
  • Delay >5 minutes risks losing the booking
Set up mobile notifications for waitlist matches.
Use location comparison to identify:
  • Providers consistently under 70% (training opportunity)
  • Providers over 90% (burnout risk, need support)
  • Variations in no-show rates by provider
Utilization imbalances often indicate booking policy issues.
Common concern: “We don’t want to be pushy”Reality:
  • 85% of clients appreciate the reminder
  • Messages are friendly, not salesy
  • Clients can opt out anytime
  • Rebooking revenue typically increases 20-30%
Let the AI handle the outreach timing and messaging.

Command Center

See how bookings originated from conversations

Dashboard

High-level scheduling and utilization metrics

Intelligence Hub

Ask AI about scheduling patterns and opportunities

Build docs developers (and LLMs) love

Get started for freeTalk to us