Launch HN: Miyagi (YC W25) turns YouTube videos into online, interactive courses

69 bestwillcui 50 5/13/2025, 12:56:42 PM
Hey HN, we’re Tyrone and Guang, founders of Miyagi Labs (https://miyagilabs.ai), an AI-powered education platform that transforms educational YouTube videos into interactive courses. It helps you learn better through active practice and personalized feedback.

We use LLMs to automatically generate quizzes, practice questions, and real-time feedback from any educational video or resource—turning passive watching into active learning. Here’s a short demo: https://youtu.be/alO7FaorHOY.

Improving education has always been tricky. Bloom’s 2-sigma problem (showing that a high-quality personal tutor is far more effective than conventional methods) has persisted, even as technology has advanced.

We met at MIT as CS majors and have always been passionate about education. Over the years, we’ve become teachers and experts in subjects like chess, algorithms, math, languages, and ninja warrior. A common theme was that we both heavily relied on YouTube to learn.

YouTube has incredible content for learning pretty much anything, but it’s buried in a lot of distractions. Also, passively watching videos is far less effective than taking notes, asking questions, and doing practice problems, which is what we aim to do with Miyagi Labs.

Our solution is essentially a multi-step function that takes in a YouTube playlist (or list of any resources) and outputs an entire course with summaries, questions, answers, and more. The pipeline is roughly: video/resource —> transcript/text —> chunks —> summary and question —> answers to questions, with some other features along the way.

We mostly use prompting and different models at each step to make the course as useful as possible. Certain topics require more practice problems vs. comprehension, and we’d use reasoning models for highly technical subjects.

We launched about three months ago and currently have 400+ courses and partnerships with some businesses and awesome creators. Some of our popular courses include 3Blue1Brown’s linear algebra course, a botany course on plants and ecology, and YC’s How to Start a Startup series.

Our product resembles classical MOOC-style course platforms in terms of UI, but is more interactive. It’s really easy to ask a question or receive custom feedback compared to a static course on Coursera. It’s also comparable to AI tutor sites, but we try to build more of a community and require less activation energy as a learner. We’re basically betting that AI can hugely improve education, but that students still want to learn from their favorite creators and want baseline shared resources for standard topics that are then augmented with personalized features.

You can try it here: https://miyagilabs.ai (no login required for most courses—but if you sign up you can also create your own course).

We’d love your feedback on what kinds of videos/resources you’d like to learn from, what’s missing from current learning tools, and if you know any creators or educators who would like to collaborate. Happy to hear any feedback and answer any questions!

Comments (50)

clamlady · 59m ago
Can you extend this into language learning content on YT? I think that would also have amazing utility. As a biologist, so happy to see Crime Pays but Botany doesn't on here. Thanks for the awesome tool. I will be using it.
ph4evers · 15m ago
Yes! I did something similar with daily exercises at https://app.fluentsubs.com/exercises/daily
andrethegiant · 10m ago
Does it work on YouTube videos that have transcripts disabled?
tdthree · 7m ago
No, it won't work for those.
pxndxx · 2h ago
Are the people that create the content okay with this?
tdthree · 2h ago
Yes. Any content that we monetize we are revenue sharing with the creator. We already have more than 5 partnerships with creators.
haswell · 1h ago
Do creators have the option to opt out?

I’m still coming up to speed on the full scope of what your product does, but I’m curious what you’d say to someone like pal2tec, who has some fairly strong and what I feel to be reasonable views about the impact of content summarization [0].

Getting direct buy-in and sharing revenue is great. But it’s not clear to me that this is the only thing that creators care about, i.e. are you still summarizing content you’re not monetizing without creator buy-in?

- [0] https://m.youtube.com/watch?v=ULUSS1-G3do

bestwillcui · 51m ago
Yep, if anyone didn't want their videos to be on our site, we would take it down.

Just watched the video, I don't initially agree with his take completely but do totally respect the viewpoint and think a payment split to the creator whenever someone summarizes the video makes sense.

Yes we do offer the option to summarize content without creator buy-in, although it seems a bit different since we're also augmenting the content with questions etc. which should drive users to watch the video even more as opposed to skip it and just read the summary.

But you're right it's not perfect. If we ever have creators who don't want their stuff on our site we'd totally respect their wishes, but that hasn't been the case right now so this seems like the best thing to do.

Cherub0774 · 15m ago
> Yep, if anyone didn't want their videos to be on our site, we would take it down.

Do note that this behavior of "opting creators into a program without their consent, justifying it via revenue share, and CYA with a 'they can opt out if they want to!' shield" is still... awful optics.

The whole Brave scandal (https://news.ycombinator.com/item?id=18736888) is a good case study on how laypeople will perceive this. It's not popular at all.

haswell · 44m ago
I do think the fact that your product is likely to drive views makes this less of a concern than what YT is doing.

From a creator’s point of view, I think the concern would be about how true this remains as the product grows/evolves.

But as long as there’s an opt-out, that seems like a reasonable approach.

solardev · 1h ago
Not to be ironic, but... is there a summary of that video? It's a bit long and he doesn't seem to get to the point for quite a while.
haswell · 1h ago
It’s an 8 minute video…and even shorter at 1.5X that will take me longer to summarize than you to watch.

But in summary, YouTube is rolling out AI summarization features on some content without giving creators any say in the matter.

Concerns include:

- Low quality summarization of high quality content will devalue the content, and in many cases is just a worse version of the content

- Impact to watch time on the channel can impact channel success over time

- YouTube is not doing anything to compensate creators for reducing watch time such as sharing revenue from viewers who primarily interact with the AI summary

But I think he articulates this much better than I did. Much better to watch the video.

seventh12 · 1m ago
The videos are the intellectual property of the creator, and YouTube has the rights to distribute and make money off of it for hosting it for you to billions of users. What's the problem? The creator can take their content somewhere else or host it themselves on their website
chairhairair · 1h ago
3b1b is a monetized partner?

Association with that brand would be very valuable.

tdthree · 1h ago
Not yet! We don't monetize his content (it's not behind a paywall). But we are talking with him :)
zoklet-enjoyer · 2h ago
Who cares?
haswell · 1h ago
The people who spend hundreds of hours carefully creating content for their viewers care [0].

The referenced video is from a photographer who has some pretty strong and reasonable thoughts on this - specifically the features YouTube itself is experimenting with.

Depending on the nature of the AI product, it has the potential to completely sideline creators.

Not saying that’s what Miyagi is doing and it sounds like they’re actually working with creators on this which is good. But the broader point is that such tools need to be thoughtfully implemented.

- [0] https://m.youtube.com/watch?v=ULUSS1-G3do

Applejinx · 2h ago
Marketers, among others
eochaid · 1h ago
This is a fun concept, and I love the name!

I’m curious why you didn’t use multiple choice for the exercises? I feel like those would be easier than typing out full answers and be closer to MOOC style homework. Maybe have a longer written question at the end of a section.

The exercises work pretty well, I like the highlighting red wrong vs. green right. It does feel a bit like the MOOC-style discussions. The tutor doesn’t just tell you the answers which is cool, but something about talking with the tutor feels a bit flat. And the flashcards weren’t very helpful for the course I picked.

I could see myself doing some courses like this with some more gamification. Being able to filter by course provider (Ycombinator, or MIT) would be cool too.

bestwillcui · 27m ago
Thanks! We do have multiple choice questions now (agreed) but some of the older courses were generated when there were only short answer.

Anything specific we could improve about talking to the tutor? Definitely will add some of those features and gamify better.

jmathai · 1h ago
I think this is a great idea. I’ve learned so much on YouTube but it’s always been in small chunks and very task oriented. I imagine there’s a lot of content Which covers broad topics that I don’t come across.

Something I’ve been doing more and more lately is asking chatgpt to create a detailed description of a topic which can be read aloud for whatever duration I plan on driving. This works exceptionally well - even for short 5 minute drives.

I wonder if the same can be done for video-based content. Sometimes I’m short on time but still want to learn something.

breakpointalpha · 1h ago
Poker, specifically Texas No Limit Hold'em, is widely taught on Youtube.

Here are some of the very best in the category, it would be really cool if you partnered with any of these.

https://www.youtube.com/@hungryhorsepoker

https://www.youtube.com/@CarrotCornerPoker

https://www.youtube.com/@PokerCoaching

tdthree · 1h ago
Poker is interesting. I think these videos do work in our current course generation process. However, I do think some subjects like poker need custom tooling around the course to really make the learning experience great. For example, access to solvers or actually playing a hand on a table is a part of the course experience as well. Chess is another one that falls in this special bucket imo. Some of this tooling is on the roadmap!
bestwillcui · 1h ago
Thanks, we'll reach out. We have a poker course from MIT (https://miyagilabs.ai/course/mit15s50) but yea these seem more practical & engaging.
skeeter2020 · 51m ago
I work in edtech and one of my teams is content creation, so pretty excited about this space but also very aware of the challenges and massive amounts of hype and over promise / under deliver. To assess I tried to generate a short (< 10m), one-video course from a YT video I've previously watched on a topic I'm an "expert" - after an hour all I see is the embedded video, the transcript and "generating content" dialog.

UPDATE: " This course failed to generate. Please try again or contact us."

I really like a lot of the components of your idea, but the execution is underwhelming. Right now it feels like you're providing middling tools for too many components without nailing any of them. Alternatively I could watch the YT video at all ready has a transcript, take notes in any tool, and ask questions to any LLM; the piece missing is context, so that's where it feels like you should focus.

Re: assessments; it feels like you're being distracted here; I'm not convinced that's how your natural target market learns in this modality. We generate quizes in our product, but it's typically used in the "internal compliance" segment - think mandatory training like food safety for food preparers - not the external (typically adult) self-improvement market (which is huge!). If you're going to do asessments you need a lot of non-AI boilerplate around tracking, validation and certification/credentials. My two cents: quizes in your app are a cool demo feature with little real value.

bestwillcui · 40m ago
Sorry we're running into some rate limits with course generation but will be fixed soon. Valid points—will respond in a bit.
vm · 2h ago
For anyone else interested in Bloom's 2-sigma, here's the original paper (1984): https://web.mit.edu/5.95/readings/bloom-two-sigma.pdf

Blows my mind that 1:1 tutoring dwarfs the impact of other factors such as socioeconomic status, reinforcement, assigned homework, classroom morale, etc (at least according to the researchers).

Does anyone know if this thesis has been replicated? Or if these results hold in modern times (original study was 40 years ago)?

WildRyc · 1h ago
The article states that Anaina and Burke separately conducted their tests, but social robots [1] have been shown to be effective in individual tutoring. Human tutoring is not always better than a well-designed computer program [2]. There have been issues with how studies interpret their effect on group size / scalability [3].

[1] https://www.science.org/doi/full/10.1126/scirobotics.aat5954 [2] https://www.tandfonline.com/doi/abs/10.1080/00461520.2011.61... [3] https://journals.sagepub.com/doi/abs/10.3102/0013189X2091279...

basch · 1h ago
Would be nice ie to see this product with focus on elementary school age content.
lassenordahl · 2h ago
Just wanna say that this is one of those magical ideas that I'd never personally think of, but when I see it like this, it makes perfect sense! So cool.
aeblyve · 56m ago
Great idea! Automated quiz generation seems like a nice use case for LLMs.
skeeter2020 · 48m ago
it's a natural extension after you use the LLM to generate the content. We do these in our content creation - and I assume learners use an LLM to answer them :)
ix101 · 1h ago
Amazing approach! Is learning a second language too different from the types of courses Miyagi was designed for, or do you see a potential for that category?
bestwillcui · 1h ago
Thanks! Definitely some potential, we actually built a language learning tool for a few days early on (but decided that it was too crowded of a space to start in).

Learning languages seems a bit different in that there's more focus on repetition compared to comprehension questions, but there are certain topics (like grammar concepts) that could work well in our current structure. Also there are some really popular YouTube channels for learning any language, so we definitely see a potential to augment those videos to more accurately & effectively learn.

CharlieDigital · 1h ago
I was actually thinking about building this because I watch a lot of YT videos in other languages (best way to do travel research is to search the destination using the local name and getting local videos).
toomuchtodo · 1h ago
Does the list of resources simply need to be a list of links to video objects?
tdthree · 51m ago
They can be links or actual files such as mp4 videos.
joshdavham · 1h ago
How worried are you about platform risk?
notpushkin · 1h ago
I don’t think they’re attached to YouTube too rigidly. (Well, I hope at least.) In theory this should work with any platform that provides subtitles. But I think if YouTube falls, or blocks their API access, they would just start hosting the videos themselves.
tdthree · 54m ago
Yea YouTube is only one format we support. Users can also upload pdfs, mp4, docx, pptx, etc. And we already do support video hosting ourselves. It wouldn't be great if YouTube decided to part ways with us, but we'd be just fine.
bananapub · 2h ago
How do you validate you’re not generating garbage, and thus teaching people nonsense?
bestwillcui · 1h ago
For official courses, we go over the generated course with the creator to vet the content. Generally they're pretty impressed but have a few things they'd like to change/add before publishing.

For self-created courses, it's generally been quite accurate and we're playing around with some eval metrics to make it as good as possible, but it's definitely a concern.

kamranjon · 1h ago
Is the course creator being impressed the most important metric? Are there other more concrete metrics you are able to use to determine quality from the perspective of a student?

I am curious if you are using any methodologies from the digital learning space like knowledge tracing to help ensure that learners are actually retaining knowledge and improving over time or knowledge mapping to understand the gaps that might exist in your content?

Do you maintain your own skills taxonomy? Are you tagging your questions or assessment events with knowledge components or skills of any kind to understand what you are testing your students for?

All of this is really cool, I’m just curious at what level you’ve gotten to on some of this because there is a very fine line in online educational content between making the students life more difficult and actually helping them learn, especially when you get into auto-generating content, and especially if you aren’t following solid principles to verify your content. (I work for an online education company and particularly in the space of training LLMs and verifying their outputs for use in educational contexts)

notachatbot123 · 1h ago
So in less promotional words:

- For official courses the creators are doing some quality control and do necessary fixes. - For self-created courses there is zero human supervision or quality control.

Is that correct?

bestwillcui · 22m ago
Yes for the first, technically yes for the second? The user can go in and change the content as well (i.e. if it's a teacher generating a course for students). But not sure what other human supervision + quality control methods you're referring to that we could implement.
fzysingularity · 2h ago
Neat idea! Do you do anything with the video itself? Understand the visual content or extract details from slides?
tdthree · 1h ago
Users can upload slides (ie. docx or pptx) and create a course from them - give it a try! For videos, we don't currently process any frames from the video just the transcript, but this is on the roadmap.
sperr11 · 1h ago
Great concept!
rylan-talerico · 2h ago
Nice work! Really cool.
karar01 · 2h ago
Good Stuff!