The fastest way to catch a misconfigured greeting, missing service, or broken transfer is to talk to your AI before patients do. Call Scripts let you do that without picking up the phone.
Open Call Scripts
Settings → AI Voice → Call Scripts
You'll see six built-in scenarios on the left and a chat-style transcript on the right.
The six built-in scenarios
| Scenario | What it tests |
|---|---|
| New appointment | Service matching, calendar availability, contact capture, confirmation SMS |
| Reschedule | Patient lookup, appointment search, slot offer, calendar update |
| Cancellation | Patient verification, cancellation reason capture, calendar release |
| Prescription refill | Refusal-to-prescribe behavior, transfer-to-clinician routing |
| After-hours | Greeting swap, voicemail vs. emergency routing, message transcription |
| General inquiry | FAQ retrieval (hours, address, insurance, parking) |
Click any scenario and press Run. The simulator plays each caller line, lets the AI respond, and shows the transcript inline.
What to listen for
After each run, scroll through the transcript and check:
- Greeting accuracy. Practice name, hours, anything time-sensitive (closed for holiday?).
- Service recognition. The AI matched the caller's wording to the right service ("cleaning" → "Adult Cleaning", "checkup" → "New Patient Exam").
- Provider names. Spelled and pronounced correctly. Edit pronunciation in Settings → AI Voice → Pronunciation if not.
- Transfer behavior. Right destination, right wording before the handoff.
- Hangup cleanness. Confirmation read back, polite goodbye, no awkward silence.
- Refusals. Refill, medical question, payment — AI declines correctly and offers an alternative.
Build your own scenario
Click + New Script in the top right. You can author either:
- Free-form chat — type each caller line, the AI responds, you keep going. Good for one-off tests.
- Structured script — define expected outcomes (e.g., "appointment should be booked", "transfer should fire") and the system flags any deviation. Good for regression testing after config changes.
Saved scripts run from the same screen with one click.
Recommended cadence
| When | What to run |
|---|---|
| Before going live | All 6 built-ins + 2 of your own real-world scenarios |
| After adding a service | New appointment + your custom script for that service |
| After changing greeting | New appointment + General inquiry |
| After changing FAQ knowledge | General inquiry covering the new topic |
| After changing transfer rules | Prescription refill (or whichever trigger maps to the new rule) |
| Weekly health check | All 6 built-ins (takes ~3 minutes) |
Replay a real call
Open any call from Calls → Logs, click ⋯ → Replay as test, and the transcript becomes an editable script. Tweak settings to fix the problem, re-run, and confirm the behavior is right before the next real caller sees it.