Speaker A
So Stanford has a research method called Storm, which has actually been shown in peer-reviewed testing to produce articles 25% more organized than the next best method.
Stanford's Storm method uses multi-agent AI to create verified, multi-perspective research reports, improving organization and reliability.
Key Takeaways
- Storm method leverages multiple expert perspectives to reduce blind spots in research.
- The multi-agent AI workflow produces consistent, verified HTML research briefings.
- Verification and peer review improve the reliability of AI-generated research outputs.
- The method is more organized and actionable than traditional single-prompt AI research.
- Nate Herk offers a free Claude skill implementing Storm for accessible advanced research.
Summary
- Stanford's Storm research method produces articles 25% more organized than other methods through peer-reviewed testing.
- Storm uses five expert perspectives—practitioner, academic, skeptic, economist, and historian—to identify blind spots and contradictions.
- The output is a verified HTML briefing that synthesizes these perspectives with ranked reliability of key findings.
- Nate Herk implemented Storm principles into a free Claude AI skill that automates this multi-agent research workflow.
- The skill runs hundreds of agents in parallel to generate dynamic workflows and deep research reports.
- Verification and adversarial peer review ensure the accuracy and trustworthiness of the final report.
- Compared to other methods like deep research, Storm produces more actionable, thorough, and risk-controlled outputs.
- The report includes a 60-second summary, practical takeaways, and clearly marked confirmed, corrected, or demoted sources.
- Users can customize the skill by providing context about their business or goals to tailor research results.
- The method simulates expert roleplay to provide diverse insights and improve research quality.
Chapters
- 00:00Introduction to Stanford's Storm Research Method
- 00:43HTML Briefing Output and Multi-Perspective Verification
- 02:05Source Confirmation and Report Reliability
- 02:41The Five Expert Perspectives Explained
- 03:25Benefits of Roleplaying Expert Agents
- 04:04Example of Multi-Agent Research in Claude
- 04:57Generating Deep Research Reports with Dynamic Workflows
- 06:03Comparing Storm to Other Research Methods
- 07:02Contradiction Mapping and Peer Review Process
- 09:35Practical Takeaways and Customizing the Skill
Full Transcript — Download SRT & Markdown
Speaker A
for completely free. And you end up with a result that looks like this. It is an HTML briefing that has been put together by five different perspectives of agents, and it has been verified.
Speaker A
So I put all of those Storm principles into my own cloud skill, which I'm going to give you guys for completely free.
Speaker A
confirmed, corrected or demoted. Meaning on the first pass, the briefing would have had information in here that just wasn't correct. But because our skill works and all this verification on V2, we can have a lot more faith in this
Speaker A
And you end up with a result that looks like this. It is an HTML briefing that has been put together by five different perspectives of agents, and it has been verified.
Speaker A
bunch of blind spots in that research plan. So, Storm utilizes these five perspectives. We've got a practitioner, an academic, a skeptic, an economist, and a historian. And each angle finds a hole that the other angles miss. And this whole idea of having different
Speaker A
Meaning, if I scroll down to the bottom, you can see that the different perspectives are giving analysis on each part of the report.
Speaker A
If you've seen other videos where I've talked about something like the roast skill or how I like to use agent teams to basically be a counsel, it's really really helpful to identify different perspectives and like I said find holes
Speaker A
But at the very bottom, you can see that we have different sources that have been confirmed, corrected, or demoted.
Speaker A
into Claude and you do a deep research command like this, you will basically be able to enter a research topic and it will spin up a dynamic workflow which will kick off hundreds of agents in the background. I think in this example,
Speaker A
Meaning on the first pass, the briefing would have had information in here that just wasn't correct.
Speaker A
report?" It gave me this markdown file, which is decent, but it's really not that thorough. And there's not as many sources as we'd like. There's only two up here and then there's a few more unconfirmed down here at the bottom as
Speaker A
But because our skill works and all this verification on V2, we can have a lot more faith in this output.
Speaker A
the storm pipeline now." I ran these five agents. As you can see, the practitioner, the academic, the skeptic, the economist, and the historian. We're converging all of that stuff together.
Speaker A
So the whole idea of Storm is that instead of just shooting off one prompt and having one angle of research, we are utilizing a bunch of different angles because if you just send off one prompt to Claude, there's going to be a bunch of blind spots in that research plan.
Speaker A
verification's done and now you have this HTML report which is consistently going to look like this every time with a 60-second summary of key findings and all of these key findings are also ranked by reliability. You can see right
Speaker A
So, Storm utilizes these five perspectives. We've got a practitioner, an academic, a skeptic, an economist, and a historian.
Speaker A
calls out the assumption that this briefing rests on and the missing sixth lens. All five lenses look at the firm from the owner's chair. Adoption rates, productivity, ROI. None of them sat in the seat of the customer or the
Speaker A
And each angle finds a hole that the other angles miss.
Speaker A
cool about this is compared to something like the deep research where it's just going to basically give you a brain dump of a bunch of stats it found, the storm research can really be tailored towards you. you can go into the skill and say,
Speaker A
And this whole idea of having different agents kind of like roleplay their own personalities and their own, you know, backgrounds with different areas of expertise is really, really beneficial.
Speaker A
all of this new data and research? And so, in this specific example with the deep research and the storm, I put this into codec, so a completely different AI model. And I said, "Hey, which one's better?" And it came back and said, "The
Speaker A
If you've seen other videos where I've talked about something like the roast skill or how I like to use agent teams to basically be a counsel, it's really, really helpful to identify different perspectives and, like I said, find holes that the other angles are going to miss.
Speaker A
It's got a much stronger thesis. It's more actionable. It's got better risk control and it's better for video and content. So, in all six of these categories here, Codeex thought that the HTML briefing was better. And I don't
Speaker A
And so let me just show you a real quick example of why that's so beneficial.
Speaker A
over 100 agents. and maybe I should take it a little easy on this deep research run because it did get hit by API rate limits. But that's also another point of like if you're going to spin up that many agents at one
Speaker A
So Claude Code natively has a feature called deep research, which launched with the dynamic workflows.
Speaker A
So anyways, I think you guys now understand the value of this report. Let me show you real quick how this actually works and how to get the skill. So, there's basically four prompts. The first one is where we tell it to spin up
Speaker A
So if you come into Claude and you do a deep research command like this, you will basically be able to enter a research topic and it will spin up a dynamic workflow which will kick off hundreds of agents in the background.
Speaker A
map. So, it's saying, "Hey, where do the perspectives contradict each other? Which one has good evidence? Which one has weak evidence?" And basically makes them analyze each other's outputs. And so, what we're doing here is we're basically just chaining together four
Speaker A
I think in this example, there were 103 different agents running.
Speaker A
just give you a prompt, give you a topic, and you do that entire thing for me. And you're going to give me a consistent template so that every time I run this, you're going to give me an HTML report that always looks like this.
Speaker A
So this will give you a pretty solid deep research report.
Speaker A
storm research, it turns one topic into a verified multi-perspective HTML briefing. It simulates five expert lenses on the topic, maps where they contradict each, synthesizes everything into a single self-contained HTML report, then adversariously peer reviews its own outputs and verifies every
Speaker A
As you can see here at the bottom, it didn't actually give me any output. It just internalized all that.
Speaker A
once you find all the information, just put it in HTML and make sure it always looks like this." So, that's just for consistency on on my end, and I really enjoy that. So, I'm going to keep going down and explaining how this works. But,
Speaker A
So I said, "Where's the report?"
Speaker A
classroom, and click on all YouTube resources, and you'll be able to find every single YouTube video and all of the resources that I've dropped associated with them. Once again, that's completely free to join. Once you have that skill, all you have to do is you
Speaker A
It gave me this markdown file, which is decent, but it's really not that thorough.
Speaker A
basically just a prompt. This is basically just a master prompt that every time I say, "Hey Claude, do storm research for me." It's going to invoke this skill. It's going to read the whole thing and then just run it for you. So
Speaker A
And there's not as many sources as we'd like. There's only two up here and then there's a few more unconfirmed down here at the bottom as well as some open questions.
Speaker A
see here I've got a folder calledcodex or agents. And you can put different skills in different types of folders based on the coding agent you're using.
Speaker A
And then I took this exact prompt that I asked in the deep research and I put it into a Storm skill.
Speaker A
storm. Then it spins up the five expert lenses in parallel and then we go into mapping the contradictions, synthesizing the report and then the adversarial pair review verification and that's where we get our output. So let me just open up
Speaker A
So I said, "Hey, Storm research, do this."
Speaker A
slash command, so it will still invoke the skill. And what you'll also notice is that this isn't very specific, so it might ask us some questions right here.
Speaker A
And it said, "Okay, cool. Here's the topic. I'm going to run the Storm pipeline now."
Speaker A
It comes back and says okay so here's the topic here is the reader and it knows that I am an AI educator and I am deciding on potentially whether voice AI agents are worth a video or if it's just
Speaker A
I ran these five agents. As you can see, the practitioner, the academic, the skeptic, the economist, and the historian.
Speaker A
And what's really cool is you can click in and see what they're doing. So if I click on the economist, for example, this is the prompt that our main session kicked off to this sub agent. So now we
Speaker A
We're converging all of that stuff together.
Speaker A
It's doing research. We can click on the academic. We can see this is the academic prompt. And once again, the academic sub aent is, you know, doing all this stuff down here. Now, while this is running, let me quickly explain
Speaker A
We're seeing where they disagree.
Speaker A
are working for this main session. So the main session talks to these five, but these five cannot talk to each other. And that is an important distinction because that's what you actually have in the agent team world.
Speaker A
And then we're going to run six more agents which are going to verify all those facts that you just found.
Speaker A
need help deciding on certain ideas or topics and I'll have them not only do research for me, but then I'll have them debate with each other. So, they'll literally argue with each other until they reach some sort of consensus. Agent
Speaker A
Verification's done and now you have this HTML report which is consistently going to look like this every time with a 60-second summary of key findings and all of these key findings are also ranked by reliability.
Speaker A
And also, if you want to check out another video where I've deep dived even more on sub agents, then you can check out this video right up here. Now, you can see all of these sub aents run on
Speaker A
You can see right here reliability high, 9 out of 10.
Speaker A
lenses are in. So, now it's going to go ahead and look at the contradictions.
Speaker A
This one was supported by the academic and the skeptic and it was challenged by the practitioner and the economist and it goes like this throughout the rest of the entire HTML report here.
Speaker A
initial passive agents had come up with. Also, I know in this video I have switched between the cloud desktop app a little bit with VS Code. If you guys have been watching me for a while, you know that I typically do like to do most
Speaker A
It also calls out the assumption that this briefing rests on and the missing sixth lens.
Speaker A
actual agents running in here. But you can see that our report has come back.
Speaker A
All five lenses look at the firm from the owner's chair. Adoption rates, productivity, ROI.
Speaker A
So that is great. We've got our 60-second summary. We've got our key findings, which obviously once again are ranked by reliability. So what I would recommend for you guys to do is go grab the skill, put it into your own claude,
Speaker A
None of them sat in the seat of the customer or the frontline employee.
Speaker A
Maybe you can play with the HTML report if you want it to look a certain way, but then do it on a topic that you do know a lot about and that's important to you in your business. and then just read
Speaker A
So that's the missing sixth lens here.
Speaker A
And maybe you even want to add a sixth lens or a seventh lens. Maybe for me in my workflow, it would be helpful to add like a beginner in AI because that's a lot of people that we're teaching are
Speaker A
And I would then just say, okay, cool. Spin up that sixth lens and run a V3 of this HTML report.
Speaker A
So, I guess the reason why I'm saying that is because I think what you should take away overall from the video is yes, go grab the Storm skill and test it out, but it's also less about this specific
Speaker A
And then it gives us really practical takeaways here.
Speaker A
more holistic research you're actually going to get. Basically, just the whole idea of if you don't have subject matter expertise, see if you can borrow it in some way. See if you can go ahead and kill your own blind spots, find the gaps
Speaker A
And what's cool about this is compared to something like the deep research where it's just going to basically give you a brain dump of a bunch of stats it found, the Storm research can really be tailored towards you.
Speaker A
this was a quick one today, but hopefully you guys enjoyed it. You learned something new. If you did, please give it a like. It helps me out a ton. And as always, I appreciate you guys made it to the end of the video,
Speaker A
You can go into the skill and say, "Hey, here's what I'm doing. Here's my business. Here's what our goals are."
Topics:Stanford Storm methodmulti-agent AI researchClaude AIAI automationresearch verificationmulti-perspective analysisdynamic workflowspeer-reviewed AIHTML research reportsNate Herk
