fentanyl ai

How to Use AI to Find Fentanyl’s Second-Order Causes

THE EFFECTIVE PROBLEMSOLVER #092

Welcome back to the hands-on problem-solving series within The Effective Problemsolver.

First, a big thank you to everyone who responded to last week’s newsletter on first-order causes!

Multiple readers chimed in on the importance of challenging AI’s answers with critical thinking.

One former colleague of mine aptly pointed out that only one causal factor—Substitution from Prescription Opioids to Illicit Fentanyl—explained why people use fentanyl, and she provided me with 10 more causal factors related to individual behavior (thanks Cristine!).

Keep those reader comments coming by replying to this email!

In Part 1, we started applying systems thinking to the fentanyl epidemic by identifying first-order causes—the direct drivers of the crisis.

But stopping there would be like treating symptoms without understanding the disease.

To really understand what’s happening, we need to go one level deeper:

What’s causing these causes?

This is where most conversations about fentanyl go off the rails.

Instead of digging into real causal mechanisms, the debate often shifts to politics and ideology—strong opinions about homelessness, border security, drug cartels, immigration, tensions with China.

But if we want to actually solve the problem, we need to move past partisan talking points and get rigorous about what’s really driving these first-order causes.

Why This Matters

Fentanyl overdoses are now the leading cause of death for Americans aged 18-45—more than car accidents, suicide, or COVID-19. 

This isn’t just a crisis. It’s a generational catastrophe.

We already identified five first-order causes with ChatGPT in the last newsletter:

But each of these has its own causes. 

And that’s what we’re going to investigate today.

Step 1: What Makes First-Order Causes Possible?

To think in second-order causes, we ask:

  • Why does fentanyl production thrive despite enforcement?
  • Why did prescription opioid restrictions backfire?
  • What forces sustain extreme potency in the drug market?
  • Why is harm reduction lagging behind the crisis?

To answer these, we have to dig into deeper structural forces that shape the crisis.

Step 2: Using ChatGPT to Identify Second-Order Causes

Here’s the prompt you can try:

Prompt:

"What are the second-order causes driving the fentanyl crisis? Focus on the top 2-3 causes of each of the first-order causes, not correlations or vague systemic critiques."

ChatGPT’s Response:

Step 3: What This Tells Us

Now we can see how the fentanyl crisis is entangled with global trade, drug policy, law enforcement, corporate influence, and public health failures.

But just like last time, we can’t take these answers at face value.

To push our thinking further, we need to ask:

  • Are these second-order causes truly driving the first-order causes? – What evidence supports these claims? What contradicts them?
  • Are there even deeper third-order causes? – For example, what caused the rise of opioid overprescription in the first place? Why do some countries handle drug crises differently?
  • What’s missing? – Did ChatGPT overlook anything? Are there hidden forces shaping the crisis that we haven’t considered?

This process isn’t about memorizing causes—it’s about building the mental habits to question, validate, and refine our understanding.

Next: The Crisis as a Self-Reinforcing System

Now we have a list of first- and second-order causes. But understanding the causes behind the causes is still only part of the picture.

In Part 3, we’ll take this one step further:

  • How do these factors interact?
  • Which ones reinforce each other in dangerous feedback loops?
  • Why does the crisis keep escalating despite intervention?

Because in the end, it’s not just about the individual causes—it’s about how they fuel each other in a system that resists change.

See you in two weeks.