Show HN: Parsnip – Duolingo for Cooking (parsnip.ai)

536 points by mizzao ↗ HN
We're building Parsnip to create a "tech tree" of cooking skills that allows anyone to level up on the building blocks of cooking knowledge while tracking their progress over time. It took us a few iterations to figure out the right product; here's the story of our latest pivot: [https://parsnip.substack.com/p/a-new-hope]

The goal is to create a personalized way to learn any recipe on the Internet, then use this as a springboard to help home cooks of all levels solve the problem of repeated meal planning in a 10x better way: [https://parsnip.substack.com/p/vision-part-one]

We believe that solving this problem at scale is good for people and for the planet [https://parsnip.substack.com/p/why-we-started-parsnip] and that now is the perfect time in history to do it: [https://parsnip.substack.com/p/why-now].

Would love any suggestions, feedback, or advice; and happy to answer any questions!

376 comments

[ 2.9 ms ] story [ 288 ms ] thread
Love it! Shared it with my husband!
(comment deleted)
Sick! I've really been wanting something like this as an extreme newcomer to cooking.
Thanks! Our whole goal is to tackle the pain of "not knowing where to start" and building up the confidence and knowledge to go and try stuff in the kitchen.

If building a new product means creating a painkiller and not a vitamin, then this is the pain that we identified among many, many beginner cooks: https://parsnip.substack.com/p/app-store-launch-stats

Awesome - downloaded it
From the privacy policy:

> We may collect the following information from you in order to provide our Services:

> ....

> Your child’s first name;

> Your child’s age or birthday;

Why?

I believe because they're targeting users under 13. I also saw this and got very concerned, until I read the beginning but of the Privacy Policy.

I'd love a clarification, say, that they don't somehow do this for adult users of the app.

> I believe because they're targeting users under 13.

This. The average age of people who watch cooking shows is ~11.

Where'd you get that number from? That's pretty interesting
Wow, if that's the average I would be very surprised. Median makes more sense, but average?
Makes it easier to sell your firstborn if they have that information already /s
My co-founder handled the privacy policy so I've pinged him to provide a response. We'll get back to you as soon as possible!

EDIT: lynndotpy was right; it's required by law under COPPA if we have users under 13. It's the same reason that sites ask people for their age/birthday to check if they're under 13.

We want kids to be able to learn to cook too!

This looks incredible! I would love a macOS app as I spend more time on the Mac than on my iPhone.

Well done for not enforcing account registration and letting me actually try the app.

Thanks. Our goal is to make learning to cook as easy as possible, and that includes making onboarding as easy as possible :-)

Re: MacOS app: is that the same toolchain as iOS, or totally different? Our iOS app is built in Swift but I'm not an iOS developer, so actually not super familiar with the ecosystem.

Apple Silicon Mac computers can run iOS apps natively otherwise you have to do some work to port it to the Mac via SwiftUI which is multiplatform framework, or Catalyst with minimal efforts otherwise as an AppKit (Cocoa) app.

What framework does it use?

I’d much prefer a website—I don’t really download apps anymore, and an application for Mac seems overkill.
OT but same. jobs was right, it all belongs in the browser. apps pose too much of a privacy and security risk.
We actually built a previous version of the app as a PWA but the experience and performance was horrible. You can still try it here: https://beta.parsnip.ai/

Warning: this is not a great user experience; it's somewhat helpful for experienced cooks but useless for beginners and product adoption was terrible.

nod and please understand that i am not criticizing your app (which looks excellent), but rather lamenting the sad state of (im)personal mobile computing.

the engineering effort would have been better spent making web technology better rather than two vastly different custom sdks with poor respect for user privacy and security.

great name , great product , team looks killer too
ooh looks cool! are yall going to support stuff like dietary preferences? and is it ad supported or?
Our main thesis is to teach the "hows" and "whys" behind recipes so that you can substitute and adjust as necessary for your own dietary preferences instead of having to find recipes that satisfy them.

It's more of an edtech approach where we try to get the right knowledge into your brain in an empowering way rather than outsourcing decision making to an algorithm.

this looks real cool. wish i could use it but i don't have a smartphone.
You're talking about targeting a billion people. Who is that billion people? Is that the western world? Or people in the world with no cooking skills?

Do you have an idea of the distribution of cooking skills in the world / western world? How many people need to develop basic skills?

There are many ways to get there but our initial thesis is to target beginners in English-speaking countries. Eventually we want to teach intermediate/advanced cooks and any cuisine to anyone regardless of where they lived.

These countries (USA, Canada, UK, Aus, NZ) have similar food cultures, a high reliance on processed foods (especially US), and relatively higher cost of labor and food vs. the rest of the world, so have a higher demand for learning to cook. The best way to see the trend and these countries is on Google Trends:

https://trends.google.com/trends/explore?date=all&q=how%20to...

Fun game: try putting something (or someone) popular on the right side of that graph and see if you can find a higher trendline

Was that the first search term you tried? ;-)
(comment deleted)
It would be great if more people would develop at least basic cooking skills. You'd be surprised how many people wouldn't even know what to do with a bag of rice if they were given one.
Took me way to long to unlock a recipe. But, the questions were good. Where is my skip to recipe button?
There are lots of ways to skip directly to a recipe all over the Internet. Tell me more, what are you trying to find?

Our recipes are actually pretty simple and not particularly special in any way. It's about the journey, not the destination ;-)

Ok, as a first time user that’s what I didn’t understand. My impatience grew, and you were saved by the fact I didn’t want to lose my progress so I powered through. Annoyed, but somewhat satisfactory end experience. I’ll have to try the recipe to see the full benefits.
Thanks for the feedback, I'll think about how to address that.

Did you realize that you could save your progress along the way and you didn't necessarily have to unlock the recipe?

Your website has a massive horizontal scrollbar for me on Firefox latest on Windows 10.

If you change the css of .slider.homepage to:

.slider.homepage { bottom: 115px; overflow-x: hidden; }

It will be fixed.

Thank you so much! In true HN fashion, you've not only identified an issue but provided a solution to it. We really appreciate it!
Awesome, I see you've implemented the fix and now it works fine. Good luck!
I love this! Already completed the "Scrambled Eggs" series. I really enjoy cooking and this is a fun way to enhance my skills, thank you!
One thing that I'd like to suggest is to make the questions a bit less ambigious / more straight forward.

E.g. One of the questions is "Which part of an upright blender is the most dangerous?". My initial reaction was the blades but apparently the answer was steam. In this case, I'd suggest rephrasing the question to "Which part of an upright blender is the most dangerous with hot liquid in is most dangerous".

Thanks, I've re-posted this in our feedback channel on Slack.
Great thanks! Just to correct my copy and paste typo, "Which part of an upright blender with hot liquid in is most dangerous?" :)
After completing "Scrambled Eggs", I unlocked the recipe but after competing "Avocado Toast" the recipe was not unlocked and I'm not sure what to do to unlock it. What am I missing?
Did you do all the levels in Avocado Toast? If so, that's a bug :(
What I really need is a browser extension that recognizes I'm on a recipe website and automatically scrolls past the recipe writer's whole autobiography to the section with the ingredients and instructions.
There are dozens of variants of this app, here's one built by a friend of mine: http://getrecipecart.com/

Like colpabar said, I think this is somewhat of a problem for experienced cooks but it's not the main issue faced by beginners, nor a big pain point. I believe this is true because I saw at least 20 startups build some version this in 2020-2021 and they mostly perished in the idea maze.

I am not a beginner myself but I would expect it would actually be a much larger pain point for a beginner. If they don't know where to start or what they need to do they may get overwhelmed by some 2000 word essay totally irrelevant to the process. Or get tripped up by extra advanced options listed in there. Just need the ingredients and the steps and maybe links to other instructions. Like if a step is "Dice the onions", link over to a page about dicing.
people make comments like this often and it makes me wonder if you actually really need it, because you can very easily find several extensions that do just that. As an experiment, I copied your comment into google verbatim, and found exactly what you are looking for.
(comment deleted)
I don't understand. But then what do I have to complain about on the internet?
I am in the process of writing my own scraper for recipe sites that grabs only the recipes and parses them into a machine readable (searchable) format. Turns out you don't need much for parsing, because an incredibly large percentage of these sites use wordpress, and either the tasty recipes plugin or wprm (wordpress recipe maker) plugin.

The only tedious part at this point is writing the different search crawlers for each site - some are reusable while others are not.

I had assumed that this would have been much more difficult, but after a weekend of writing the cheerio utils for pulling the recipes only from tasty or wprm tags, I found myself nearly done. The frontend and search engine tuning will take much longer.

It would be really cool if recipe sites could just include a recipe instead of a useless blog post punctuated by ads every 4 sentences, but these people clearly don't want me using their site in the "right" way. Oh well.

Recipes cant be copyrighted, so bloggers write long-form narratives ahead of the recipe to make the contents of the page intellectual property.
a substantial number of people (not me) do enjoy reading the stories, they get something out of it, damn normies.
Me too, but not when I'm in a rush, but the JS is flashing off and on, moving things around the page, and generally making for a miserable experience.

Maybe they could just put it after the recipe???

Isn’t Google responsible for this? They rank results based on how long users stay on the page, plus how much they scroll. Forcing all those “when I was a girl in Sicily…” stories at the top of a recipe that nobody wants.
Source?

My understanding is Google wants pages to be different and have a lot of keywords.

If you have a generic recipe website with just the simple cooking instructions:

1. it's going to have less key words

2. it's not going to look different from hundreds of other websites like this

(comment deleted)
I’d add a browser extension that reroutes from or preloads content from sights that load as you scroll like the link for this does.
I've found that a lot of the recipe sites I use have a button that takes you directly to the recipe (after all I'm told that the life story is for SEO purposes). I just am so used to skipping over the cruft that I skip the button as well.
I remember there being a very good extension that did exactly this.

It got review bombed by food bloggers, and they ended up taking it offline.

This is awesome. Would love to buy food-type packs from an app like this!

Like, “Teach me the basics of Salads”, or “Advanced stir fry recipes”.

Thanks for sharing about willingness to pay — the bete noire of consumer apps :)

One of our eventual goals is to transition to a creator-driven system where anyone can teach others about how to cook, and monetize that too. There is so much food knowledge hiding all over the world waiting to be shared.

How will this make money?
Ooh, that's a great question. We're building in the open and writing about it at https://parsnip.substack.com/ so if you subscribe, you'll see the answer in a future issue!

Otherwise, if you're a seed investor I can pitch you? :-D

I found duolingo extremely frustrating when I tried to practice a language I already had some knowledge in. It forced me to do a bunch of stuff I didn't care about. As most people will have some knowledge of cooking I think applying this concept to cooking is a bad idea.
What did it force you to do that you didn't care about? I don't have any other language skills but it offered me ways to test out to higher levels and such. I figured that would get people with knowledge to a better spot.
It was a few years ago now so I don't can't recall the details. But the way I remember it, the testing out system was better than nothing but not good enough.
Yeah, it doesn't seem good for that at all. It bogs you down in things that are very easy (or even encourages you by gamifying flawless performances.) Even if you test out of units, the farther you move along, the more you realize that Duolingo sets up a very specialized arbitrary mapping of translations from English to the target language as you learn. If you've skipped ahead, you'll be missing questions because you translated "waste" as "malgastar" instead of "desperdiciar." Couldn't be more frustrating.
What's with the numerous throwaway astro-turf-y comments from low-activity accounts?
I honestly don't know. It's just me from the team that uses HN.

Truthfully, one of them is an angel investor who saw us of his own accord and decided to say hi. But maybe the others just really like the app?

I don't get it. there are literally millions of people offering free cooking videos on youtube, and getting better at cooking isn't difficult at all - you just follow instructions (often in video) and try over and over again until you find something you like.

Is this sort of like a meal service without the delivery of ingredients?

Our idea is that as a beginner/novice, trying to find the right free cooking video, and getting better through repeated trial and error,

is inferior to

knowing that you have trustworthy information, a path to improvement, and the ability to track your progress over time.

Re: meal service without delivery of ingredients...yes! That's basically what experienced home cooks already do. But there's a few steps before we get there. Here's the vision: https://parsnip.substack.com/p/vision-part-one

I'll admit its been many years since I was a novice at cooking but it seems like its going to be a big challenge monetizing something you can get for free from hundreds of thousands of sources with detailed video instructions.

You might have a very narrow niche of 'nerdy enough for cooking app, not nerdy enough to search on youtube and doesn't want video instructions' which is a lot more limited than any beginner cook.

From my experience once you find someone on youtube whose videos you like their video history is a huge library of recipes from them, so it isn't always difficult to look through youtube and find recipes - I have a double handful of channels I know and like and earning credibility isn't their challenge given their videos wide success.

I haven't seen an recipes. Do you only support US measurements (cup, pint, oz, quart. etc)?

That would be a pity.

We actually think recipes are mostly unimportant, but teaching the underlying principles are what's important. Measurements are more important for pastries but less important for stovetop/oven cooking.

The recipes we have right now are pretty easy for any English speaker to use. Our main content creator is from Australia, lives in Canada, and makes fun of the Imperial system all the time :)

American living in Germany. The thing you're not understanding is that "use roughly an ounce or so" will mean nothing to anyone in Europe. It's not about "recipes aren't important" but speaking the language of people who use your app. Locality is just as important.
I mean honestly though, if your problem is not being able to figure out unit conversions with a smartphone in your hand you might be putting the cart before the horse trying to learn how to cook well.

Learning to "eyeball things" is actually one of the most important skills I think you can have in the kitchen (not for baking of course), but when I see that I need 200g of an ingredient for a recipe, my first thought isn't "I can't believe the person writing this is from Europe!"

OTOH, it would literally take a few lines of code for the app to have conversions ready to go for you.

... but my hands are full, messy, or contaminated when I'm cooking, and your condescending arguing point kind of flies out the window at that point.
This looks great! I will definitely be trying it out.

I haven't seen this asked or answered anywhere and am curious - how do you guys plan to make this profitable? Charging for more "advanced" features? Ads?

I already have the Duolingo owl chasing after me for money (and more time).

In my opinion the ad-based business model is mostly dead. We'll have to find a new one.

We're building in the open at https://parsnip.substack.com/ and you can subscribe if you'd like to follow along with how we figure out the business model!

Thanks, and best of luck!
I like the idea but it would be good if the recipes were tied to skills. It also doesn’t matter if you select a different level, you can still only pick the same things. It would also be good to select vegan or keto or gluten free to customize choices. The dishes seem very limited after starting, there’s nothing I don’t already know how to make. On the positive side I like that there’s no need to create an account to get started since I’ll probably delete this from my phone now that I’ve checked it out.
Right now we're mostly focused on beginners and don't have more advanced content / more international cuisines yet. But we have some baking and Ukrainian dishes landing soon!

Is that what you mean by recipes tied to skills, or something else?

What is the technology stack for your app?
Native iOS, native Android, and Firebase.

At this stage of a product, iteration speed matters more than anything else.