Turn Claude into a PhD-level researcher in 5 minutes

What STORM actually is

STORM stands for Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking. It was published at NAACL 2024 by the Stanford OVAL Lab, and in peer-reviewed testing it produced articles about 25% more organized than the next best method.

Here's the part that matters: you don't need the software. The Stanford method is really a way of thinking, and you can run that same thinking inside Claude with four copy-paste prompts. That's what this page is. Nav Toor wrote the four-prompt version and it went viral for a reason — it works. Everything below is his, lightly formatted so you can grab each block and go.

Why one prompt will always fall short

When you ask Claude "tell me about X," you get the majority view. The most common framing. The surface. What you don't get is the practitioner who works with X every day, the skeptic who thinks the field is wrong, the economist who follows the money, the historian who has seen the pattern before.

Those voices all see different things. That's what a PhD student does — they don't ask one question, they ask five. Multi-perspective questioning catches the blind spots single-prompt research never sees. The four prompts below run that process end to end: five perspectives, then the map of where they clash, then a synthesis, then an honest self-review to catch what the synthesis got wrong.

1. The multi-perspective scan

This is the heart of the method. Replace the topic in line one. What comes back is five very different reads of the same subject — the practitioner sees what the academic misses, the skeptic challenges what the practitioner assumes, the economist exposes incentives the academic ignores.

I need to research [YOUR TOPIC].

Simulate 5 different expert perspectives on this topic:

1. THE PRACTITIONER: works with this daily.
What do they know that academics miss?
What practical realities are usually ignored?

2. THE ACADEMIC: has studied this for years.
What does the peer reviewed evidence actually say?
Where does the evidence contradict popular belief?

3. THE SKEPTIC: thinks the mainstream view is wrong.
What is the strongest counterargument?
What evidence do proponents conveniently ignore?

4. THE ECONOMIST: follows the money.
Who profits from the current narrative?
What financial incentives shape the research?

5. THE HISTORIAN: has seen similar patterns before.
What historical parallels exist?
What can we learn from how those played out?

For each perspective give me:
- Their core position in 2 sentences
- The strongest evidence supporting their view
- The one thing they would tell me that no other perspective would

2. The contradiction map

Now make the model find where the five voices fight. The fights are where real understanding lives. Most people skip this step — it's the one that separates a surface read from actual expertise.

Based on the 5 perspectives above, map the contradictions:

1. Where do two or more perspectives directly contradict
each other? List each conflict with the specific claims
that clash.

2. Which perspective has the strongest evidence?
Which has the weakest? Why?

3. What is the one question that, if answered, would
resolve the biggest contradiction?

4. What does EVERY perspective agree on?
(This is likely true. Even opponents confirm it.)

5. What topic did NONE of the perspectives address?
(This is the blind spot in the whole field.
Often the most valuable finding.)

3. The synthesis

Pull everything into a briefing no single expert could write. It accounts for every angle, names the contradictions, ranks reliability, and lands on a specific action. Swap in your own role on the fourth point.

Synthesize everything from the 5 perspectives and the
contradiction map into a research briefing:

1. THE ONE PARAGRAPH SUMMARY: explain this topic as if
briefing a CEO who has 60 seconds and needs nuance,
not just the headline.

2. THE 5 KEY FINDINGS: most important things I now know,
ranked by reliability. For each, note which perspectives
support it and which challenge it.

3. THE HIDDEN CONNECTION: one non obvious link between
findings that only shows up when you look at all 5
perspectives together.

4. THE ACTIONABLE INSIGHT: based on all the evidence,
what should someone in [YOUR ROLE] actually DO
differently? Be specific.

5. THE FRONTIER QUESTION: the one question that, if
answered, would change everything about how we
understand this topic.

4. The peer review

STORM has one known weakness Stanford's own researchers flagged: it doesn't self-critique, so source bias and shaky claims sneak in. This prompt makes the model grade its own work — strong claims, weak claims, biases, missing angles.

Now peer review your own research briefing:

1. CONFIDENCE SCORES: rate each of the 5 key findings
on a 1 to 10 scale for reliability. Explain each score.

2. WEAKEST LINK: which claim are you least confident in?
What specific info would you need to verify it?

3. BIAS CHECK: which perspective might be overrepresented
in your synthesis? Did one voice dominate?

4. MISSING PERSPECTIVE: is there a 6th angle I should
have included that would change the conclusions?

5. OVERALL GRADE: if a Stanford professor reviewed this
briefing, what grade would they give and why?
What would they tell me to fix?

The 5-minute workflow

Run them in order, in the same chat, so each prompt builds on the last:

1. Minute 1. Prompt 1. You have five expert views.
2. Minutes 2–3. Prompt 2. You have a contradiction map.
3. Minutes 3–4. Prompt 3. You have a research briefing.
4. Minute 5. Prompt 4. You know what's reliable and what isn't.

A PhD student takes 40 to 60 hours to produce this by hand — not because they're slow, but because reading from five angles, mapping contradictions, synthesizing, and self-critiquing is genuinely a 40-hour job for one brain. Use it before writing anything, before a big decision, before an interview or a negotiation, before you learn a new skill. Any time a confident-but-shallow answer would cost you.

How I used this on my own company

I'll be honest about why I built this page. For a few weeks I'd been going in circles on one question: should the content engine my co-founder and I are building be a self-serve product, or a done-for-you service? I kept flip-flopping. One day I'd watch some creator on X claim he stood up an AI business in an afternoon and think we were doing it all wrong. The next day I'd talk myself back off the ledge. I couldn't tell if I was being impatient or if I was actually missing something.

So I ran STORM on it. Exact question, five perspectives. The skeptic and the historian said the thing I'd been avoiding: I was fusing two different businesses in my head and calling it one. The economist made me price out the tradeoff I kept hand-waving. The contradiction map showed that the disagreement between me and my co-founder wasn't a disagreement at all — we were describing two rungs of the same ladder. Then the peer-review pass called out that I'd let the cautious voice dominate, and named the one advantage I was under-weighting.

None of that was new information. It was all in my head somewhere. STORM just forced the angles I was too close to see, in about ten minutes, and the decision that had felt stuck for weeks suddenly wasn't. That's the whole pitch: it's not smarter than you, it just makes you look from the seats you'd never sit in on your own.