I am more concerned about the cost step up from Gemini 2.5 Flash to 3.5 Flash, with the latter being roughly 3x more expensive. I thought the intention of the Flash models was to be relatively low-latency and more affordable compared to Pro, but the newer Flash models aren’t being priced as such. Then again, the era of cheap and plentiful AI might be coming to an end…
I posted this in another comment but couldn't help but notice this discussion since it seemed relevant. I've been working on https://mealsyoulove.com, which is a meal planning app that also integrates with Kroger and Instacart for ordering groceries. Jow looks similar (not sure what their pricing model is?), but I'm leveraging AI to build highly tailored recipes and meal plans while allowing you to also import your own recipes to incorporate.
Basically personalized meal planning and grocery integration. Since the Show HN I posted a couple months back I've been incorporating user feedback to add things like meal prepping, better ingredient reuse across meals, and cooking style preferences.
One of the biggest points of feedback has been adding more grocery stores but I'm really limited by who has APIs to actually integrate with, which is basically just Kroger and Instacart. Walmart has an API but ignored my API access request. Would love to hear if anyone has ideas on how to approach this.
I get the skepticism as I shared similar thoughts on what recipe quality would be like. I'm also quite sensitive to AI slop. My wife, who really is an outstanding cook, was even more skeptical, and she has a _very_ high bar for recipes. To be clear, we don't use it to generate recipes for every meal. She has a collection of go-to favorites and then peppers in 1-2 AI recipes throughout the week, often to explore new things. She also uses it to create "Quick Bite" recipes for when we need something fast with whatever we have on hand, outside of an actual meal plan.
Honestly, I wasn't sure if the AI recipes were going to meet her standards when it comes to food, but so far she's been quite happy overall with the recipe quality. She often will request replacements or customizations, so the first pass suggestions are not always what she's looking for.
I realize it's definitely not for everyone though.
I'm sorry you hit that as it should definitely respect instructions around things like protein sources and ingredient selection. I'll take a look at that.
Not at all a nitpick, it is one of the things that is painful in the app IMO. I think the length of time for some of the operations is one of the bigger reasons for people to bounce after initial sign up. I need to think if there are some clever ways to improve the onboarding experience such as trying to pre-generate some recipes during/after the onboarding flow.
You're right that Meals You Love integrates with Instacart and Kroger for ordering meal plan groceries but it's not primarily a grocery funnel and this has no impact on meal plan construction. Really these are just value-add integrations IMO. For our family, the real value is actually providing a means for us to save our favorite recipes and get AI-recommended recipes peppered in. The grocery ordering is secondary, though quite useful for us.
The second big value prop for us has actually been the new "Quick Bites" feature which generates recipes based on ingredients you have on hand (either tracked in your pantry in the app or simply input manually). For instance, we'll often have some ingredients we want to use up but need suggestions on what to make. In this case, there's no grocery integration at all since we're using entirely stuff we already have.
Good question on the meal calendar. You CAN share meal plans (as well as recipes), though there isn't a calendar as such beyond the weekly meal plan view.
Preferences are primarily handled via the AI (uses Gemini on the backend) and this is the primary driver in how recipes are constructed and recommended.
Ah, I hear you on the onboarding wizard. I did my best to keep it streamlined but understand it's still overwhelming. Hard to balance keeping it light with collecting enough data to provide reasonable recommendations.
The meal plan generation does take a bit, _typically_ it's around 90ish seconds but it does vary a lot. That's odd the images are loading slowly, I'll need to look into that.
You can ask for meal replacements (with or without input instructions) from the meal plan view. The replacements are not particularly snappy though. Trying to balance efficient usage of AI with a snappy UX is tricky.
It's actually a pretty decent API. I've hit some quirks with it, but for the most part works reasonably well overall. The best part about it was there were no hoops to jump through to start using it.
Totally agree on a video walkthrough, and it's on my list. I've mostly been putting it off because I'm not sure if I'm capable of making a polished enough presentation, which is a bad excuse.
Also 100% on messaging to differentiate from just using an LLM to do this yourself. This one feels a bit harder to me because I think it perhaps is not obvious until you get into the product and use it for a bit, though the integrations are a pretty good concrete example.
My experience with graph DBs: schemas usually become implicit and ad hoc, minimal tooling support and even less mature tooling, difficult to explore and understand your data, performance is often poor, memory usage can be problematic because they usually pull the graph into RAM, and there are few people with real experience (comparatively to traditional DBs) which can create a negative feedback loop.
I have yet to run into a use case where a graph provided more value than a relational model. I'm sure they exist, but I haven't found them yet.