Comment by aaviator42
7 days ago
On the same topic: does anyone have an API concept that they wish existed and that they'd be willing to pay for?
7 days ago
On the same topic: does anyone have an API concept that they wish existed and that they'd be willing to pay for?
Local grocery prices. Let me upload a shopping list and allow me to optimize for cost (visit this store for these items, this store for these items) and a trail to follow through the store for optimal pathing.
Same thing for home improvement - Lowe’s in stock indicator is wildly wrong to the point that I sometimes call and ask an employee to go physically look at the item.
If you are seriously interested in this, then I would appreciate your answers to these questions! What is the specificity of your shopping list? Cheerios 12 oz, Cheerios, cereal, etc.? If cereal, is it a standin for the all the cereals you usually buy? How consistent is your list? Do you change what you buy significantly from week to week? What causes you to substitute other items for your usual items? And do you do it to save money, try new things, a little of both, something else? If you had Cheerios 12.5 oz on your list, but one of the retailers near you had a significant promotion on the family size, would you want that instead? Let’s say you put “healthy cereal” on your list and you wanted the best price on all healthy cereals. Does that mean organic, low sugar, whole grain, something else? Do you think it would be possible to figure that out from your purchasing history? How much money do you think you would have to save to visit 2 stores? Do you have loyalty program membership at all your nearby grocery retailers?
I was kind of thinking about this as well! But in the end I kind of thought it would be something I would just build for myself. As in I often go to a few different grocery sites in nyc as ones super close, another is 5 mins further. And then there’s random little markets that have better deals on fruit. I walk by them all the time. Could perhaps be quite easy to make a little front end where you fuzzy find the food item with search and select qty options and insert the price.
For groceries at least, the time cost + fuel cost of buying from different stores would probably cancel out any minor variations in prices
Hm, I am equidistant from 3 different grocers and sometimes 15 dollar steaks are marked down to 10. I think you're right with a variered enough basket the sales will be a wash but maybe if I let the algorithm decide what my diet is that week based on what's discounted the most I could save some dollars. The thing that actually keeps me loyal to one store is I'm familiar with the floor plan so it doesn't take 5 minutes to find the hot sauce, so I would love a wayfinder for unfamiliar stores. Could be a good app for ambient competing / meta raybans.
depends on where you live. in european cities you tend to have multiple grocery stores within walking distance from each other. also you don't have to go to all of them on the same day. i delay buying certain things until i have a chance to go to the place where those are cheaper. it just takes a bit planning ahead.
>For groceries at least, the time cost + fuel cost of buying from different stores would probably cancel out any minor variations in prices
Sure, but alternatively, using the same data you could find out what the whole list costs at each store and just go to the cheapest one.
What do your eyes tell you? https://youtu.be/P7KBcsdPhxA?si=RNDXSwiHqCKDLv0i&t=107
For customer projects I am happily using paid "text to speech" APIs from several vendors.
Privately, I would like to use an API, which gets my Lego bricks inventory and returns all sets which I could build. Further it should show me sets, which I almost can build and show me missing pieces. Also e.g. it should show me sets with slight color differences, e.g. I have bricks in yellow but originally it requires orange. Things like that...
Sounds a lot like rebrickable. I'm not sure if they have an API though
That's a funny idea :)
I think the first one should be very much doable, but I am not sure how I would build the "almost complete" and the "similar colors" features.
I guess calculating the Levenshtein distance between the sets would work somehow?
Edit: scratch that, just intersect the set of available pieces with each set. If there are fewer than n--or m%--missing pieces, suggest those.
not sure if there are APIs, but there are a couple of websites that do that for Lego already.
not an api but, Internally we’re just looking for a native text to speach app that auto records all meetings and call a webhook with the transcript. not the notes! for some reason all most rmeetings apps gives you only notes and seldomly a webhook or similar. also not interested in zapier etc.
After two weeks off looking for a solution, we’re going to vibe code something basic and use deepgram. If we just skipped the shopping around, the solution would be live already..
Recall.ai is exactly this. Using them at my current company and it works well. It even supports live transcription.
Aah nice. I knew about them but did not see they have a desktop sdk
2 replies →
This is included in Microsoft Teams.
Will even auto detected who spoke, transcribe, video records and AI summarize it (with defined actions / next steps).
You can set it up to auto perform once the first person joins the meeting.
>This is included in Microsoft Teams.
This, and there are also 3rd party bots that work with Teams (and presumably other video chats as well) that will join the meeting and do their own transcription. I've seen a couple of on meetings with vendors lately, it'll join and be called something like x company transcription bot.
3 replies →
Many meetings happen that are not on teams.. So that would only do for 10%.. Id like to meet the teams where they are working instead of telling them to change how they work.
1 reply →
I was working on a work based STT system (I assume that's what you meant, not text tk speech) but might have to add in a webhook as well. What's the use case you need it for, just storing the transcripts somewhere?
We want to process the transcript to build up project context. Making it easy for team members and customers to ask project questions and brainstorm ideas with a chatbot
1 reply →
Sure, but the API itself is the easy part, especially with LLM help. The problem is the data source is a total trash fire, so in order for it to be worth it the API cost would either be exorbitant or not worth it.
You know what's pretty good at cleaning up data that's a total trash fire? _More_ LLM. :-)
I run a web service whose primary purpose is cleaning up messy, SEO-enshittified data from Google, eBay, etc. After years of fine-tuning my own heuristics, I threw a super-cheap LLM at it and it massively out-performed my custom code. It's slower, but the results are well worth it.
This thread is a really really good example of why this kind of question sounds good but can lead you astray. So many folks have been generous with their answers here but a huge portion of them have multiple replies with existing solutions that were a simple google away, which means they thought of a neat idea but they definitely were not desperate enough for a solution to even search for one let alone pay for it.
Those kinds of ideas can still become real businesses, especially if you have a great way to get awareness of your solution out to people who aren't actively looking for that, but you're better off trying to find problems where people have tried throwing money at every solution out there and are still yelling for help.
Tl;dr try to sell "pain killers" not "vitamins".