Products

Everything you need to run your practice communications.

Use Cases

See how practices put Front Desk to work every day.

View all use cases

Case Studies

See how practices across 8 specialties recovered $600K+ in revenue with AI-powered call handling.

View case studies
Quick Links
Home/
AI Receptionist/features
Pricing/pricing
Contact/contact
Book a Demo/contact
About/about
Partners/partners
Security/security
Developers/developers
to selectTab to navigateEsc to close

By Industry

DentalOptometryMedicalVeterinaryMedical SpaPlastic SurgeryPhysical TherapyMental HealthPrimary CareView all industries

By Role

Practice OwnersOffice ManagersFront Desk StaffView all roles

Enterprise

Dental Service Organizations (DSO)Medical GroupsVision GroupsVeterinary Chains

Call Management

AI ReceptionistCall RecordingCall IntelligenceMissed Call Text BackVoicemailPhone Porting

Scheduling

Smart SchedulingOnline SchedulingCalendar SyncWaitlistBooking Widget

Patient Engagement

Two-Way TextingRemindersReview RequestsPatient OutreachRecall & Reactivation

Practice Management

Multi-LocationTeam ManagementDigital FormsPaymentsPatient CRM

Analytics & AI

Call AnalyticsPractice AnalyticsProvider DashboardCustom AI Voice
AI ReceptionistVirtual Receptionist24/7 Answering ServiceAfter-Hours AnsweringHoliday Call AnsweringMissed Call RecoveryOverflow Call AnsweringVoicemail ReplacementAI Call Answering ServiceAppointment Booking ServiceOnline Appointment SchedulingHIPAA-Compliant AISpanish-Speaking AIReplace Your Answering ServicePricing vs Answering ServiceCost of an Answering ServiceAnswering Service Pricing GuideView all use cases
Templates & ScriptsCase StudiesIndustry GuidesHealthcare GlossaryBlogIntegrationsResultsChangelog
Tools
Get StartedLog InSales: (469) 812-5544

The AI said something wrong on a call

There's no thumbs-down button on a call — the way you "correct" the AI is by giving it better information. Open the call in Calls → Logs, find what it said, and decide whether the mistake came from missing knowledge (fix in Knowledge Base) or wrong settings (fix in AI Voice). For one-off hallucinations on something it shouldn't have answered at all, restrict the topic via the Knowledge Base or Custom Knowledge field.

Updated May 27, 20263 min read

First: figure out what kind of "wrong" it was

Open the call in Calls → Logs, find the moment, and ask yourself which bucket it falls into:

Type of mistakeExampleFix path
Under-informed"I don't think we accept that insurance" when you doAdd the real info to your Knowledge Base
Stale dataWrong hours, wrong holiday closure, wrong provider nameFix the underlying setting (Locations → Hours, Team, Services) — the AI reads those, not a prompt
Wrong scopeQuoted a price you don't publicly quote, or commented on a clinical questionAdd a Knowledge Base entry stating the rule ("we don't quote prices" or "clinical questions → message + callback")
HallucinationInvented a service, a fee, or a policy that doesn't existSame as wrong-scope — give it the actual policy in writing. The AI prefers knowledge-base text over guessing.
Persona / toneSounded too casual / too formalSettings → AI Voice → Conversation Tone

The fix loop, in 4 steps

  1. Find it. Calls → Logs → open the call → read the transcript. Copy the exact wrong phrase.
  2. Categorize it using the table above.
  3. Fix the source of truth. The AI doesn't have a "correction" knob — it has inputs. Update the right input:
    • Wrong facts about your practice → Settings → AI Voice → Knowledge Base (you can paste text, upload a PDF, or crawl your website)
    • Wrong hours/services/team → fix the actual setting (Locations, Services, Team)
    • Wrong tone → Settings → AI Voice → Personality & Behavior
    • Wrong greeting → Settings → AI Voice → Custom Greeting
  4. Test it. Call your number and try the scenario that broke. If the new answer is right, you're done. If not, the knowledge entry probably needs to be more specific — see below.

Writing knowledge-base entries that actually fix problems

Vague entries don't work. The AI reads them like a person would.

Weak — "We have flexible scheduling." Strong — "Same-day appointments are available Monday–Thursday between 9 AM and 11 AM if a slot is open. Call back the same morning or check the booking link."

Weak — "Don't talk about prices." Strong — "Do not quote prices over the phone. If a caller asks about pricing, say: 'Pricing depends on what you need — I can have someone email you a quote, or you can book a consultation. Which would you prefer?'"

Concrete, actionable, and ideally including the exact phrase you want the AI to say.

When the AI is making things up that you never told it

That's a knowledge-gap symptom. The AI's general training contains a lot of medical/business-y patterns, and when it doesn't have your specific policy it will sometimes fill in with a plausible-sounding default.

The fix is to take away the gap: add the policy. Even a one-line entry that says "For [topic X], take a message and have the office manager call back — do not answer questions about X directly" is enough to stop the hallucination on that topic.

See Train on your FAQs for the full Knowledge Base flow (paste, upload, or crawl).

If a mistake harmed a patient

Open a support ticket immediately with the call ID. We will review the transcript and the recording, and if the issue points to a model-level problem (not a knowledge gap) we'll escalate to engineering.

Frequently asked questions

Is there a "thumbs down" or "flag this" button on call logs?
Not today. The fix loop is structural — you find the mistake in the transcript, then update the AI's knowledge or settings so the next call gets it right. We're considering an inline flagging tool; tell support if you want it sooner.
The AI made up a price we don't charge. How do I stop that?
Add the correct pricing (or the rule "we don't quote prices over the phone") to your Knowledge Base. The AI checks the knowledge base before answering specifics; once the right answer is there, it will use it instead of guessing.
The AI gave the wrong hours. Why?
Almost always because your Hours of Operation in Settings → Locations is out of date or doesn't reflect a holiday/recent change. The AI reads those hours directly — fix them there, not in the AI prompt.
The AI told a patient something medically wrong.
Stop using the AI for that topic. Add a Knowledge Base entry that explicitly says "for clinical questions, take a message and have a clinician call back." The AI follows knowledge-base guidance over its general training. If the issue is urgent, also enable the relevant clinical rule.
Will training on FAQs erase the mistake immediately?
Yes, on the next call. The AI loads your knowledge base fresh each call. There's no model retrain delay — once you save, the next caller gets the new behavior.

Was this article helpful?

Related articles

Still need help?

Our team replies fast. Or just ask the in-app Setup Assistant.

Contact support