Why health is the hardest place to put AI: three things that changed how I build

Description and use

<p>In most jobs, when an AI is wrong, you fix the draft. In health, you might not get the chance.</p> <p>I'm John, a senior AI and full-stack engineer. I spent the last year building a health-information assistant, <a href="https://tabibu.health" rel="noopener noreferrer">Tabibu</a>, and I'm starting this series with the question I get asked most: why is health so much harder than the other places I have shipped AI?</p> <h2> 1. A mistake costs more </h2> <p>A wrong dose is not a typo. In a normal product, a bad answer costs a retry. In health, someone may act on it. So I stopped asking "is the

Problem

<p>In most jobs, when an AI is wrong, you fix the draft. In health, you might not get the chance.</p> <p>I'm John, a senior AI and full-stack engineer. I spent the last year building a health-information assistant, <a href="https://tabibu.health" rel="noopener noreferrer">Tabibu</a>, and I'm starting this series with the question I get asked most: why is health so much harder than the other places I have shipped AI?</p> <h2> 1. A mistake costs more </h2> <p>A wrong dose is not a typo. In a normal product, a bad answer costs a retry. In health, someone may act on it. So I stopped asking "is the

Outcome

<p>In most jobs, when an AI is wrong, you fix the draft. In health, you might not get the chance.</p> <p>I'm John, a senior AI and full-stack engineer. I spent the last year building a health-information assistant, <a href="https://tabibu.health" rel="noopener noreferrer">Tabibu</a>, and I'm starting this series with the question I get asked most: why is health so much harder than the other places I have shipped AI?</p> <h2> 1. A mistake costs more </h2> <p>A wrong dose is not a typo. In a normal product, a bad answer costs a retry. In health, someone may act on it. So I stopped asking "is the

Evidence

Why health is the hardest place to put AI: three things that changed how I build

Source