How we keep AI safe in a clinic: seven rules

Before software talks to your patients, you should be able to answer three questions about it. What is it allowed to do? What does it do when it isn't sure? How would you find out if it went wrong?

If a vendor can't answer those in plain words, the trouble isn't the AI. Nobody wrote the rules down.

Here are ours. They apply to every job on our list, from Gigi, Intuo's AI receptionist, answering the phone to the packets prepared for prior authorization. None of them depends on the AI having a good day.

1. Every job acts from a short list

A job can only take the actions on its list: check open times, book an approved service, send a confirmation, send a deposit link, email your desk, put a caller through. If an action isn't on the list, it can't happen, however the conversation goes.

You decide what's on the list for your clinic. We bring those decisions to you as a one-screen table of yes-or-no answers, prefilled with the sentence Gigi would say. A few sample rows:

Sample rows. Every clinic fills in its own.

Where a rule matters, software enforces it. The AI can't talk its way past any of them.

Your medication list, checked by code, decides which refill requests go to your provider. Your hours, read on every call, decide whether a caller is put through. Your deposit rule sets the amount. And anything Intuo proposes to send to patients who didn't contact you, like a recall batch, waits in your dashboard's Queue. Nothing in the Queue sends without a person's approval.

2. Clinical lines are never crossed

Intuo never prescribes, never suggests a dose, never interprets a result, never tells a patient a symptom is normal, and never reads the chart aloud or confirms to anyone else that someone is a patient.

A problem after a treatment gets its own path. Here's how it runs.

1. 9:47 PMA patient texts that her lip is swollen and hot, two days after filler.
2. 9:47 PMBefore any AI reads the message, it's checked against the urgent phrases the owner approved. It matches.
3. 9:47 PMAn urgent alert goes to the clinic's team, with her name, her treatment and her words. It's never treated as a sales lead.
4. 9:48 PMOnly after the alert is delivered is she told that her message has reached the team as urgent. Words that suggest something severe get a plain instruction to call 911.
5. 9:58 PMThe nurse watching urgent alerts that night calls her back. Intuo raised the alert. The nurse made every clinical decision.

Because that check runs before the AI sees a text, an AI outage can't swallow it. After every call, the transcript is checked again for the same warning signs, in case something slipped past during the conversation.

At our first clinic, the owner approved the list of 68 phrases that count as urgent before it went live. The first real report came in on September 30: the patient was put through to the desk, and the urgent email was delivered.

3. Testing mode comes first

Before a clinic goes live, its texts can reach only approved test numbers, and anything held back is logged with who it would have reached. The one exception is a patient who has just called or booked: for the next hour, they get the texts about their own request, like a booking confirmation. Reminders, follow-ups and recall texts don't reach your patient list until you say go.

When we need to test something new, we add a tester to the approved list. We never switch the protection off to test.

4. Every call is reviewed, and every change is versioned

Every morning, the previous day's calls are checked against your rules. The review looks for a price you haven't approved, a guess at how many units someone needs, a promise to text a link that never went out, a transfer that didn't really happen, and a call that didn't end cleanly. When it finds one, we fix the cause.

Every change to your clinic's settings is saved as a new numbered version, so any change can be undone by putting the earlier version back. Every day, a separate check compares what's running on your phone line with what was set up, and flags any difference.

5. Done means confirmed

A system saying "request accepted" isn't the same as the thing happening, and we treat them differently. A booking counts when it shows up in your EHR. If the chart rejects a booking or never confirms it, we get a text within minutes. A desk request counts when the email is delivered. Payments are read back from your register.

The same rule runs through your dashboard. Money that has been paid is labelled Measured. Anything projected, like the value of a recall batch nobody has booked from yet, is labelled Estimated. The audit log records every approval, change and view, by person, alongside what Intuo did on its own.

From mid-September to October 1, Intuo sent the desk at our first clinic 160 emails, and all 160 were delivered.

6. A quiet day is written down, not left blank

A job that did nothing and a job that never ran look the same unless someone writes down the difference. So the daily call review, the booking watch, the follow-up texts and the call-back check each record every run, empty ones included, with the reason they were empty: nothing was due, the patient had already booked, the caller wasn't a quick hang-up.

When one of them goes quiet, the record says why, so a slow day never gets mistaken for a broken one.

7. HIPAA compliant, with a signed BAA

Intuo is HIPAA compliant. We sign a BAA with every clinic before go-live. Call recordings are private and can only be reached through an authenticated request. Patient texting is carrier-approved: the carrier reviewed the exact messages patients receive. A patient who texts STOP stops getting every kind of message from us, and marketing texts respect quiet hours.

Questions to ask any AI vendor

Use these with us or with anyone else.

1. What can it do in my systems? Can I see that as a list?
2. What does it do when it isn't sure?
3. What will it never say to a patient?
4. Who decides what it's allowed to say, and how do I change that?
5. How do you test before it texts my patients?
6. How do you know a booking actually landed in my EHR?
7. If something breaks at 2 a.m., who finds out, and how?
8. Will you sign a BAA?

Specific answers mean you're talking to someone who has run this in a real clinic.

To hear Gigi working under these rules, try her at our demo line.

How we counted: desk emails from the email service's delivery records, September 14 to October 1, 2026. Urgent phrases from the clinic's approved list.