I believe your question answers itself, if you could do this then people would[2]. The next question might be 'What prevents the current LLM based coding tools from being able to do this?"
Now there has always been software that people have used that they "could" write for themselves but they didn't because they didn't want to maintain it. Seems like things that are like that would be good candidates for this right?
But this question shares at least a spiritual geneology with the response to some new startup code that does some thing, and the comment here is "Gee, I can't believe that got this funded, I could write that in a weekend."
The problem is, there are many things that are easy to describe but difficult to pin down, and reality is complicated. So many times I've gone into a project thinking it would be "easy" only to start uncovering layer after layer that are much more involved than I expected.
So no, you cannot '1-shot prompt' pretty much any significant software, and that goes doubly true if it affects your life in any potentially devastating way.
One of the things I'm constantly amused by[1] is the Solitaire program on iOS that is clearly being vibe coded these days because it comes up with daily challenges like 'win a hand in -2739551 moves'. Like no human would ever write code that screwed up basic math but LLMs do it all the time.
[1] Obviously I am easily amused :-). But it is sort of the 'pelican riding a bike' test where you can easily tell what a human would do vs what an LLM does.
[2] EDIT: another commentator says they vibe coded it in a weekend. That would support the hypothesis that the application could be at lease a small number of shots vibe coded. That said, I'd love to see that code and the prompts that led to it.
A lot of people use "one-shot" things not to sell it or provide links but for personal usage and to replace tools etc they used to pay for (as few did in this thread).
But if I had a coworker/employee just constantly finding ways to one-shot tools we're paying for I'd be pretty miffed. If that's all they're doing why are they even there. Just use their salary to pay for the services at that point.
Fable built me a version that covered all of my needs in an hour. (Clients pay me via ACH/wire - maybe it would have taken a day if I needed a stripe integration?). Runs on localhost with SQLite - incredibly basic, but I enjoy it twice as much as Harvest.
I used my Harvest data export and generated PDF invoices as the majority of the “spec”.
Feels silly to open source this, given how little effort it was… (and because I’m certainly not going to respond to others PRs) but I’m happy to if anyone wants.
Love this. Lots of software companies are sitting on no moat. Not talking about Harvest, but your JIRAs just jam a bunch of crap that most people don't need and then have to raise prices to justify it, before PE comes along.
A software company's value is not just providing software, it's providing reliable software at a good price. The 'good price' for a ton of stuff has plummetted.
Me too. I told Claude to use Beancount for the ledger (I don't want probabilistic accounting!), and very quickly I had a little Go/SQLite/React webapp and some Python scripts that do everything I needed. Since then I've added little tweaks as necessary.
There's a time tracking page where I enter hours by project, and an invoice generation page where I select what to include and get a nice PDF invoice. The Python scripts import my bank statements and auto-reconcile expenses and invoice payments. They connect to Ramp, Expensify, and Gusto APIs for expenses, and maintain a consistent folder structure for reciepts. There's a script to give me monthly cash revenue figures for local taxes and let me know how much excess cash I have for owner distributions.
It's exactly what I need and nothing I don't, has no recurring cost, and it's completely private (all runs on my laptop).
Note, however, that I'm still using Gusto, because they take some responsibility for getting my payroll taxes right, and filing them.
I think it's including pay for usage. From the pricing page, beneath both Teams and Enterprise:
> Your base rate includes core features. As your team grows, additional invoices, projects, clients, and tasks are billed based on what you use, so you're never overpaying.
That's a bit bewildering, lol. Especially since they have annual plans.
This clarifies it:
> On Flex billing your first (sign-up) invoice usually covers seats only, because no projects, tasks, clients, or invoices have been tracked yet. Usage-based charges are calculated from the previous billing period, so they first appear at your renewal — not at sign-up. This is why a bill can jump (e.g. from a seats-only $44 to $404 once usage is added).
You're right something doesn't ad up, and seems fishy (to me, bizarre even). But that isn't the author, it's Harvest after the Bending Spoons aquisition.
Those are seat fees, which do not include the new usage fees. I got this email:
> “Looking at your account, you're currently on the Basic plan at $40.00/month with 5 seats, and you're scheduled to renew … on the Enterprise Unlimited plan at $586.50/month…”
So, from $40 to $586.50 for “unlimited” use. Same product. I think the goal was to force everyone onto usage based plans. I dropped spare seats and shifted off unlimited, and its about $75/mo per seat.
But if someone wanted to take over angry Harvest customers, it would probably be a good little business. Guess I just need to rip the bandaid off, and let a prompt run overnight.
We recently went through a version of this with Asana when we discovered their "per seat" pricing is sold in groups of 5 seats. Going from 5->6 users brings your bill from 5->10 seats, doubling your price.
It isn't about the money, the principle is gross. Thankfully Asana's core business is now a prompt. We are nearly done replacing it with a native, self hosted client. Will post about it once it is hardened through use. Cancelling our subscription Asana this week.
To SaaS providers (myself included) it has never been easier to leave your service due to mistreatment. Take note.
That’s what I thought. I wonder if that’s true though. I’m sure 80% take no time but actually productizing it takes forever. Now you’ve got a maintenance burden too. I’m really curious how long it would take to implement harvest and the ecosystem around it these days.
It took me about 10 days to update an existing business app that I used to include functionality replacing harvest time tracking, invoicing (with a far superior QBO sync, saving us days of people time per month), and forecasting (Forecast was never well integrated with Harvest).
Yes, we are picking up a maintenance burden but the 10x price increase in our case made it a very easy cost/benefit equation, and I decided that as a primary technology in a consulting business it was worth controlling it.
If it's an internal app, you stop adding features when you have all the features you need.
I've vibe-rebuilt several apps for myself and after a certain point I don't feel like anything is missing so I just stop touching it entirely except to fix a rare bug here and there.
Home grown product isn't going to match a saas product's features. But you dont need most of it anyway. so home grown gets the job done. Till it hits entropy or the roi is gone. Problems will show up a few months / years down till it isn't worth the effort or the savings.
Saas products that survive this AI wave are going to come out stronger on the other end.
I argued this before. I think it makes no sense for eg an estate agents to vibe code a CRM, but if you're a tech firm (or a big firm with a tech department) I think it is worth a shot, especially if you only use 50% of the features in the software you pay for.
So, you’ve spent a good amount of time on it, to where you hope there’s only a week left, it does a lot less, is less accessible, you can’t fully use it yet, and it’s buggy.
I think the only lesson for SaaS providers, yourself and myself included, is how willing people are to cut off their noses to spite their faces. :)
Similar story here, except we went from Jira to a custom Plane.so build. Everyone from product to engineering loves it, gets features they want added quickly. And for me, I mainly have Claude keep track of everything (mcp).
The Jira billing administration will remain as a business school case study of dark patterns for years. Can't wait for the EU to put their nose into it.
Loom was another recent one. $10/month -> 200 something. Why? Apparently people with the same domain as me now required an account including developers who left the company 3 years ago.
Not saying I like their business model, but if they acquire a company, 10x revenue, lose half their customers, and keep margins the same... they've quintupled that company's profits.
I've had a Harvest account for over a decade, and it was always admittedly a little bit too cheap. But two months ago, they changed the pricing based on what you gross, so essentially putting a flat tax on my earnings.
I knew it was going to be more expensive, but when I got the bill this month and saw the price was over $200 and then noticed the Bending Spoons LLC tagline at the bottom, that was the end.
Claude is backing up all of my data via the API and will be vibe coding my next invoice.
Judging by the conversation elsewhere in the thread, the pricing page isn't nearly clear enough to capture the real impact. I'd wager that'll be true elsewhere as well.
Mercury bank handles invoicing quite well. If you're manually preparing invoices (as I assume OP is given the need to include hours), invoicing is free. Obviously payments are included (cards via Stripe).
They have recently expanded into bookkeeping, but I haven't used that. If you're just using the bank account & manual invoices, it's free.
Used Bonsai happily for years before that. I see they have been bought by Zoom, so I would expect some changes.
I started with mercury recently and absolutely love it. The Books stuff seems to be OK, which is a huuuuge improvement over QuickBooks Online which is now an unwieldy pile of crap that nobody should use.
As of Jan 1 Mercury says they will start charging $30/month, which is cheaper than other alternatives I've found. My vibecoded Beancount-based system probably cost me more in time than using a year of Mercury Books.
Damn, I've been trying to get another job for pretty much this entire year to work up to the $240/yr, now it's going to be $360/yr? That sucks. I mean, I'd pay a lot more for Mercury, but it sucks that I probably won't get to take advantage of the $240 for my first year.
I'm guessing because there are some NSFW pictures that show up at a large size as son as you click on the "photos" page? Surprised they don't just block access to that specifically, instead of the whole website
Also an NSFW warning might have been nice on that page link, website owner. Hopefully the IT guy at work will understand
Bending Spoons recently bought MileIQ, the drive tracking, quick classification & team drive reporting app that we use for our vehicle logbooks for the Australian Fringe Benefits Tax record-keeping requirements. Going to have to find a new solution now! Mostly likely something OSS. I might even ask Claude/Codex to integrate that app’s background tracking features into our own staff iOS app, so I don’t need to rely on an underpaid OSS iOS dev for the App Store publishing!
I know a lot of people who have been laid off when Bending Spoons acquired their company so I'm a little miffed when I see this.
I had to use Harvest when I did some consulting last year. I don't know the revenue numbers for Harvest. But, the company that asked me to use Harvest was a tiny software consultancy. I always assumed Harvest was something small companies used, not big ones.
Those small companies would be very sensitive to price changes, and very motivated to use Claude to build their own alternative if it meant keeping $100 in the bank.
I think this might be the moment when Bending Spoons business model is exposed. I cannot imagine large enterprises using Harvest en masse and those are the only companies who will stick with BS (pun not intended) when they run their playbook. Small orgs will certainly take five minutes with Claude. This isn't a SaaS that is really sticky.
It's a shame. They tried to increase our prices about 800%. I actually liked the software and used it for over 15 years across a couple of services businesses.
They do have this "usage based pricing" where you pay them for each user, but then also for each project and customer, and then a percentage of your billings. It's completely absurd to be paying them a percentage when you receive payments by wire and all they're doing is emailing an invoice.
Anyhow caveat emptor. Looking at their website they do not show the actual pricing. They just say it's "starting from" $9/seat or $14/seat, but you only pay that if you don't use the software at all.
As far as I can tell, what Bending Spoons has figured out is that they can raise prices 8-10x, but only maybe 60-80% of their customers will cancel because it's a big hassle, and so the profits go up massively for a while. They will probably even retain a hard core of say 10% of their original userbase for some time.
Used Harvest for many years. Was talking to an agency owner friend of mine who had been using it, but once Bending Spoons jacked up the price they jumped for their own self-cooked version.
The "SaaS is dead" narrative is a bit overblown, but private equity needs to think twice before gouging folks these days.
This law seems really hard to write, doesn't it? And what's Bending Spoons done that should actually be wrong? I could imagine such a law helping them. As a small company, companies Bending Spoons is making opportunity for me to build competing products at a price people actually like (in my case, it's actually IBM, but similar disregard for customers). So please, Bending Spoons, buy more companies so we can get some churn on these companies. As long as we can avoid regulatory capture.
What people don't realize is that if the business sold in the first place it's because the original owners weren't being able to make it profit as it should
Economies of scale are a big deal, hence why the comparison between the Stripe fee and Harvey fee is meaningless
(of course you're free to go to the competition or Vibe your own, but then you start noticing the actual cost of the service vs value added)
Should try PotatoTimer! It's a bit different, I haven't built a stripe integration into it, but it's something I've been building for myself for my freelance work and for tracking my time learning piano, working out, etc.
I haven't shared it around much (not fully finished) so any feedback would be welcome. It works offline, no account needed.
113 comments
[ 0.28 ms ] story [ 142 ms ] threadNow there has always been software that people have used that they "could" write for themselves but they didn't because they didn't want to maintain it. Seems like things that are like that would be good candidates for this right?
But this question shares at least a spiritual geneology with the response to some new startup code that does some thing, and the comment here is "Gee, I can't believe that got this funded, I could write that in a weekend."
The problem is, there are many things that are easy to describe but difficult to pin down, and reality is complicated. So many times I've gone into a project thinking it would be "easy" only to start uncovering layer after layer that are much more involved than I expected.
So no, you cannot '1-shot prompt' pretty much any significant software, and that goes doubly true if it affects your life in any potentially devastating way.
One of the things I'm constantly amused by[1] is the Solitaire program on iOS that is clearly being vibe coded these days because it comes up with daily challenges like 'win a hand in -2739551 moves'. Like no human would ever write code that screwed up basic math but LLMs do it all the time.
[1] Obviously I am easily amused :-). But it is sort of the 'pelican riding a bike' test where you can easily tell what a human would do vs what an LLM does.
[2] EDIT: another commentator says they vibe coded it in a weekend. That would support the hypothesis that the application could be at lease a small number of shots vibe coded. That said, I'd love to see that code and the prompts that led to it.
But if I had a coworker/employee just constantly finding ways to one-shot tools we're paying for I'd be pretty miffed. If that's all they're doing why are they even there. Just use their salary to pay for the services at that point.
I used my Harvest data export and generated PDF invoices as the majority of the “spec”.
Feels silly to open source this, given how little effort it was… (and because I’m certainly not going to respond to others PRs) but I’m happy to if anyone wants.
Post for the planet? (power/water usage)
An unregistered lurker somewhere is too lazy, shy, or scared to ask, but they’ll start prompting soon :)
A software company's value is not just providing software, it's providing reliable software at a good price. The 'good price' for a ton of stuff has plummetted.
There's a time tracking page where I enter hours by project, and an invoice generation page where I select what to include and get a nice PDF invoice. The Python scripts import my bank statements and auto-reconcile expenses and invoice payments. They connect to Ramp, Expensify, and Gusto APIs for expenses, and maintain a consistent folder structure for reciepts. There's a script to give me monthly cash revenue figures for local taxes and let me know how much excess cash I have for owner distributions.
It's exactly what I need and nothing I don't, has no recurring cost, and it's completely private (all runs on my laptop).
Note, however, that I'm still using Gusto, because they take some responsibility for getting my payroll taxes right, and filing them.
- Free (obviously free)
- Teams $9 a month
- Enterprise unlimited $14 a month
The writer of this article claims they got upgraded to $133.98 a month plan, but looking at the site, such plan does not even exist.
Something is a bit fishy here or they accidentally added an extra 3 to the $13.98 or mistook the yearly price for a monthly price.
You can have those lower monthly fees if you pay a higher percentage of your billings.
The article acknowledged that.
> There’s also a “flex” plan which costs $12.65/mo… but that plan now skims an additional 2% on top of the usual ~3% card transaction fees.
> Your base rate includes core features. As your team grows, additional invoices, projects, clients, and tasks are billed based on what you use, so you're never overpaying.
That's a bit bewildering, lol. Especially since they have annual plans.
This clarifies it:
> On Flex billing your first (sign-up) invoice usually covers seats only, because no projects, tasks, clients, or invoices have been tracked yet. Usage-based charges are calculated from the previous billing period, so they first appear at your renewal — not at sign-up. This is why a bill can jump (e.g. from a seats-only $44 to $404 once usage is added).
https://support.getharvest.com/hc/en-us/articles/31447072608...
You're right something doesn't ad up, and seems fishy (to me, bizarre even). But that isn't the author, it's Harvest after the Bending Spoons aquisition.
> “Looking at your account, you're currently on the Basic plan at $40.00/month with 5 seats, and you're scheduled to renew … on the Enterprise Unlimited plan at $586.50/month…”
So, from $40 to $586.50 for “unlimited” use. Same product. I think the goal was to force everyone onto usage based plans. I dropped spare seats and shifted off unlimited, and its about $75/mo per seat.
But if someone wanted to take over angry Harvest customers, it would probably be a good little business. Guess I just need to rip the bandaid off, and let a prompt run overnight.
My first tech job ever pretended we were supposed to track our hours in harvest. Which of course no one did. So long ago.
It isn't about the money, the principle is gross. Thankfully Asana's core business is now a prompt. We are nearly done replacing it with a native, self hosted client. Will post about it once it is hardened through use. Cancelling our subscription Asana this week.
To SaaS providers (myself included) it has never been easier to leave your service due to mistreatment. Take note.
What do you mean? Like a claude code one shot prompt?
Not OP, but definitely not a one shot prompt. However because of AI it takes far less resources to replicate services like these rather quickly.
Yes, we are picking up a maintenance burden but the 10x price increase in our case made it a very easy cost/benefit equation, and I decided that as a primary technology in a consulting business it was worth controlling it.
Trying to understand what the LLMs mean to the saas world. Will you have to become a time tracking/invoicing pro? Where’s the break even I wonder.
I've vibe-rebuilt several apps for myself and after a certain point I don't feel like anything is missing so I just stop touching it entirely except to fix a rare bug here and there.
Home grown product isn't going to match a saas product's features. But you dont need most of it anyway. so home grown gets the job done. Till it hits entropy or the roi is gone. Problems will show up a few months / years down till it isn't worth the effort or the savings.
Saas products that survive this AI wave are going to come out stronger on the other end.
I built a markdown editor and viewer to better than the best I've bought or used in the macos App Store in 81 prompts.
I've built a very good ticketing system and it took a lot more prompts than that.
I think the only lesson for SaaS providers, yourself and myself included, is how willing people are to cut off their noses to spite their faces. :)
Berkshire Hathaway invests further $330M in Bending Spoons
https://investors.bendingspoons.com/newsroom/berkshire-hatha...
I knew it was going to be more expensive, but when I got the bill this month and saw the price was over $200 and then noticed the Bending Spoons LLC tagline at the bottom, that was the end.
Claude is backing up all of my data via the API and will be vibe coding my next invoice.
Example: https://news.ycombinator.com/item?id=50420733
They have recently expanded into bookkeeping, but I haven't used that. If you're just using the bank account & manual invoices, it's free.
Used Bonsai happily for years before that. I see they have been bought by Zoom, so I would expect some changes.
As of Jan 1 Mercury says they will start charging $30/month, which is cheaper than other alternatives I've found. My vibecoded Beancount-based system probably cost me more in time than using a year of Mercury Books.
https://github.com/harvesthq/chosen
Also, hope your night is going well. I'm quite tired!
Also an NSFW warning might have been nice on that page link, website owner. Hopefully the IT guy at work will understand
But then I thought I am on a 5g travel router in the UK and they have more rigid blocking with a lot of false positive so I just assumed it was that.
I had to use Harvest when I did some consulting last year. I don't know the revenue numbers for Harvest. But, the company that asked me to use Harvest was a tiny software consultancy. I always assumed Harvest was something small companies used, not big ones.
Those small companies would be very sensitive to price changes, and very motivated to use Claude to build their own alternative if it meant keeping $100 in the bank.
I think this might be the moment when Bending Spoons business model is exposed. I cannot imagine large enterprises using Harvest en masse and those are the only companies who will stick with BS (pun not intended) when they run their playbook. Small orgs will certainly take five minutes with Claude. This isn't a SaaS that is really sticky.
They do have this "usage based pricing" where you pay them for each user, but then also for each project and customer, and then a percentage of your billings. It's completely absurd to be paying them a percentage when you receive payments by wire and all they're doing is emailing an invoice.
Anyhow caveat emptor. Looking at their website they do not show the actual pricing. They just say it's "starting from" $9/seat or $14/seat, but you only pay that if you don't use the software at all.
As far as I can tell, what Bending Spoons has figured out is that they can raise prices 8-10x, but only maybe 60-80% of their customers will cancel because it's a big hassle, and so the profits go up massively for a while. They will probably even retain a hard core of say 10% of their original userbase for some time.
I guess the original owners just wanted out and Bending Spoons was the best option for that.
The "SaaS is dead" narrative is a bit overblown, but private equity needs to think twice before gouging folks these days.
And yet, they never do.
Economies of scale are a big deal, hence why the comparison between the Stripe fee and Harvey fee is meaningless
(of course you're free to go to the competition or Vibe your own, but then you start noticing the actual cost of the service vs value added)
I haven't shared it around much (not fully finished) so any feedback would be welcome. It works offline, no account needed.
We were able to build a replacement in an afternoon with the features we use.
I know less technical orgs arent quite there yet, but the moat on this stuff is surely evaporating quickly.
really eats into margins for what should be simple
that being said, I can also see that the market can bear it
there is still room for undercutting competitors or rolling it out yourself much easier now, but only for your specific use case