# Medical AI Boundary Table

Use with [AI Is Not a Doctor - and It Is Not an Emergency Service](/articles/ai-is-not-a-doctor).

> If you or someone near you may be having a medical emergency, contact your local emergency
> number now, or go to the nearest emergency department. Do not use this worksheet as a
> substitute for that step, and do not describe an emergency to a chatbot before calling for help.

## Before you type: a 30-second self-check

- [ ] Am I asking the model to organize or explain something in general (green/amber), or am I
      asking it to tell me what is wrong with me, whether it is serious, or what to do about my
      medication (red)?
- [ ] Is there any chance this is urgent? If yes - stop, this is red. See the contacts below.
- [ ] Am I about to type a symptom into a chat because the clinic is closed and this is easier
      than waiting? Name the actual next step (pharmacist, after-hours line, emergency care)
      before you continue.

## The full table

| Zone | Use case | Examples | Why | What to do instead, if not green |
| --- | --- | --- | --- | --- |
| Green | Organizing your own notes, preparing appointment questions, understanding a general term | Turning symptom notes into a short timeline; asking what a medical term means in plain language | You supply the facts and keep every clinical judgment | - |
| Amber | General information about a condition, medication class, or test category you already have a name for | "What does this type of test generally measure?" (not "is my result normal") | General information can be accurate and still not apply to your specific case | Confirm anything personal with your pharmacist or clinician before acting on it |
| Red | Diagnosis, treatment comparison, medication changes or dosing, urgency judgment, any emergency symptom | "What could this be," "is this serious," "should I stop taking this" | No exam, no license, no accountability, and a measured unsafe-response rate in published research | Contact your local emergency number, your pharmacist, or your treating clinician - see contacts below |

## Naming your contacts now (before you need them)

Fill this in while calm - it is much harder to look things up under stress.

- My local emergency number: ____________________ (look this up yourself; do not rely on an AI
  tool to confirm the correct number for your country)
- My pharmacy's phone number: ____________________
- My clinician's office number, and their after-hours line if they have one: ____________________
- The nearest emergency department to where I usually am: ____________________

## A green-zone prompt template

```text
Here are my rough notes: [paste your notes, including dates]. Organize
this into a short, factual timeline I can read to my doctor in under
two minutes: what happened, when, and what I want to ask. Do not add
any interpretation, likely cause, or urgency level - just organize
what I gave you, in my own words.
```

## An amber-zone prompt template

```text
In general terms, what does [test name / medication class] typically
do or measure? I am not asking you to interpret my personal result or
situation - just explain the general concept so I can ask my
[pharmacist / clinician] a more informed question.
```

## Fixed wording when a chat drifts into red

Copy one of these into the chat (or say it to yourself and close the window):

```text
Stop. I am asking for a clinical judgment you cannot make. I will
take this to my pharmacist / clinician / local emergency number
instead. Do not diagnose, triage, or suggest medication changes.
```

```text
This is no longer an organizing question. Closing this chat and
contacting a licensed person now.
```

If the red-zone issue is emotional crisis rather than a physical symptom, switch to [AI is not therapy](/articles/ai-is-not-therapy) and use the contacts on that page (local emergency services or [IASP](https://www.iasp.info/suicidalthoughts/)).

## Review this table

Print it or save it somewhere you will actually see it again - not just in a chat history you
might not reopen. Revisit it the moment a health-related conversation with an AI tool starts to
feel like it is answering a question only a licensed professional should answer.