STORM Method
- STORM = Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking
- A research method from Stanford OVAL Lab, published at NAACL 2024
- Core idea: don't ask one prompt. Research a topic from 5 expert angles, find where they fight, synthesize, then self-review.
- In Stanford's tests, multi-perspective articles were 25% more organized and 10% broader in coverage than single-prompt ones.
- You don't need their code or tool. Run the same thinking in any LLM (e.g. Claude Code) with 4 prompts.
Why one prompt fails
- One prompt gives the majority view. The surface.
- It misses the practitioner, the academic, the skeptic, the economist, the historian. Each one sees different things.
- Where the 5 voices disagree is where real understanding lives.
Prompt 1: Multi-perspective scan
Replace the topic in line 1.
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
Prompt 2: Contradiction map
Make the model find where the 5 voices fight.
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.)
Prompt 3: Synthesis
Pull everything into one research briefing.
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.
Prompt 4: Peer review
STORM's known weakness: it doesn't self-critique, so source bias and fact misassociation sneak in. This prompt makes the model grade its own work.
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?
Workflow
- ~5 minutes total. Prompt 1 → 5 expert views. Prompt 2 → contradiction map. Prompt 3 → research briefing. Prompt 4 → reliability check.
- Output: a multi-perspective briefing with contradiction analysis, synthesis, a specific action, and a reliability score.
When to use
- Before writing, a big decision, interview prep, investing, learning a new skill, negotiation, or a presentation.
- Related: AutoResearch