I recently did this for myself using https://tiller.com/ to sync checking/credit-card transactions to a Google Sheets spreadsheet. Then a GitHub action mirrors the spreadsheet to a free Supabase database.
From there, Supabase MCP or psql gives Claude/Codex access to the transactions/balances for english queries. Really impressed with their ability to find subscription patterns, abnormal patterns, etc. Also to predict cashflow which no online tool so far is good at i.e. "tell me how much cash I can move to savings based on my monthly spend patterns and available cash".
For autocategorization, I learned Claude is really good at custom DSLs. Had it create a markdown table based ruleset to normalize payee/categories. I also run the autocat rules as part of the GitHub actions.
I'm doing something similar with Tiller (which I've been using since Mint was acquired by Intuit).
It's neat to see how OP did this using a Claude Routine though. My version locally uses a local qwen model + an API key (annoyingly created using OAuth) with sheets access. A Claude Routine would've been significantly easier
Routines are so fun to work with. It's almost too easy to spin a new one up. A little worried about when I get past the 15 routines limit, though. Then it goes into "extra usage" land.
That's so cool! Are you planning to open source any of this? Would love to see how you set everything up, or - maybe most interested in - some of your prompts.
I've been using Tiller since the pre-AI era. Plaid seems to be more B2B oriented so I haven't looked into it. But eventually yes that would be ideal to own the full pipeline.
Maybe my net worth is too low but I just don't see a value proposition. I don't want daily emails from LLMs and if I need updates on my investments any more often than quarterly (at most), I should probably seek safer investments. I am a bit interested in budgeting tools, but I want them to be completely deterministic. For me at least, financial planning is pretty uneventful and time spent optimizing expenses more than I already have would be better spent seeking a higher paying job.
Have to be careful with routines. There’s a very small disclaimer that’s barely noticeable that in routine mode all MCP tools, even write are always allowed. So agent can technically go rogue and start mutating your resources via MCP.
This seems like a solution looking for a problem. https://tiller.com/ works great and lets you do whatever calculations you want in a spreadsheet - and, bonus, it's never going to hallucinate.
I don't quite understand the desire to have these verbose summaries that you have to read from LLMs. You'll notice anomalies if you just categorize each of your expenses every so often (easy with Tiller).
This. It's really cool to weave other data sources into your data.
I recently needed to set up some calendar events on certain dividend days, but of course, didn't know what those dividend dates actually were. So we used the MCP connector to retrieve our current Vanguard holdings, had GPT-Pro do web research to pull all the dates, and then created calendar events from that. Worked well.
When I was trying to use Claude to analyze my past transactions, I found out that it was constantly hallucinating charges, sometimes adds new, double counts and etc.
When I'm dealing with my finances the 95% time Claude is correct and doesn't hallucinate is not enough as I have to be vigilant and review its work all the time. So it kinda makes it worthless in this case for me
To everyone who doesn’t know how Plaid works: You give your banking username and password directly to Plaid, and it keeps it (so it can continue to login).
I don’t understand how anyone is OK with this. It goes against every security principle and it’s against the terms and conditions of every bank.
I realize that almost no bank provides a secure and proper API to get info and/or to transfer funds, but Plaid’s solution is a disaster waiting to happen.
Hear you 100%. It felt very uncomfortable for me the first time I used it, as well.
The problem is that there sort of isn't a better way right now in the US, and for now, Plaid or a Plaid-like competitor is the safest way. Eventually, it would be awesome if there were clean, open APIs, and standards around this, but for now, it's the best we have.
The alternative of course for the DIY-er is some sort of browser automation, which honestly, is what I tried first. I really wanted it to work, but it didn't - which led us to Plaid.
Super cool writeup from a technology perspective. And a motivator to build more tools, play with MCP and try out Claude routines. The product pitch is also really clear. Good job all around.
Now for the criticism:
back in the day mint.com was mind-blowing. It's what you always thought you'd wanted. The graphs were interactive and pretty and you really loved seeing them go up. Not so much down. I was so attached to the gamified aspects, much like step counters. They reinforce habits.
My mint journey ended with roughly 5 years or so of data, once they sold to Intuit, didn't like the ads and willingly syncing all my data to mega-corp. Much like Duolingo, it felt good at the time, but I don't know that it did anything for me at all.
Tracking is a double-edged sword: it really does build better habits. It's better to track weight every day for example so you better understand that fluctuations are mostly noise. The daily tracking stuff is entirely useful to get the need to track daily out of your system.
TLDR: checking my net-worth daily sounds like something I should coach myself out from. Ironically that probably takes tools, but the end goal is to not need them.
Awesome feedback. Agree 100% with this. I guess a couple comments:
- We have a built-in CSV export tool in beta right now for cash transactions, and plan to add this for other datasets as well. You should be able to download your data when you want it. It's yours.
- Yes, tracking is great, but it also has a dark side. My sort of vision, at least for what I want, is less of a gamified finance tracker and more of an ambient, always-on agent that's watching for me. It knows my preferences, it knows what I care about, and it tells me when it finds something.
- Before we get there though, for now, it's really interesting to sort of tinker and build your own custom finance automations. As a programmer, it just feels liberating to get the data out of some closed banking app and into a space I'm comfortable in.
- Especially from an investing standpoint, it's been neat to pair our MCP with a much smarter model like 5.4 Pro and have it do long-horizon research tasks that require a lot of web research and correlation.
> As a programmer, it just feels liberating to get the data out of some closed banking app and into a space I'm comfortable in.
Quote of the week for me. well said.
~15 years ago I fumbled around with web programming basically because I never learned how to use excel in school. Nerded out with css, html, forms, then php and mysql to script together an unbelievably worse version of what a spreadsheet could do, but it was incredible that I could build something entirely made for my idea. And with the power to improve it.
Thank you for writing and sharing your story, it's motivating and comforting even. Good luck!
I don't really get this; could just use Plaid and have your own transaction/net worth site/app in a few hours with Claude Code and it'd be much more consistent.
That's actually one of the best things about the current moment -- it's getting easier and easier to do things yourself, and there's less and less reason to use someone else's tool. It's sort of raising the bar for all the apps out there.
It's pretty straightforward! There's a widget in the app that you auth through, and then you give consent for the data pull through Plaid. This authorizes the first data pull, and then webhooks come in going forward as data changes.
For the non-Plaid assets eg., home, car, etc., we just added custom asset MCP tools so you can manually add those and they're included in your computed net worth.
Used driggsby the other day. Friend of mine sent it to me. Suprising how easily it found all of my subscriptions. That was the main reason i tried it. I'm sure i'll dive deeper into it this week though.
I'm surprised y'all stopped at the personal finance layer. I've been thinking for awhile that LLMs would be really effective as personal financial advisers, and this kind of hookup (plus I guess another one for investment accounts?) seems like all that's needed to bootstrap reasoning.
Yup! Actually starting to experiment with that now.
Just this morning, we stood up a demo email agent (basically, email back and forth with Claude with our MCP server connected, providing the data) and it's strangely comforting to chat with it. There's something about the medium of email and how it just works because that's where you're already used to talking with your financial advisor.
There's a lot of nuance in how it's built though, and everyone has different preferences, so to start with the focus is really on building an agent-friendly MCP.
I think it's rather hard because of their security & contractual requirements -- we had to sign a contract with them, go through security review, and so on.
We just this week launched a new sign-up flow to make it waaaay easier for non-businesses to use Plaid, I posted some details below.
Actually, as part of publicizing our new hobbyist-friendly onboarding, we're looking to work with hobbyists who have created Plaid-powered apps and would be interested in making a short video about their app and their Plaid experience to potentially be featured on the Plaid blog -- if you're interested, shoot me an email at ahoffer@plaid.com and I can send you the details.
I reached out to them a couple years ago with this exact question and was told flat-out no. You might be able to sneak around it with an LLC but I think they also require you to have a public website for a plausibly banking-related business, which altogether seemed like too much effort to fake for what I wanted out of it.
So you don't have to be a business to use Plaid, but you do have to be a business to buy Plaid via the Sales channel rather than via the self-serve channel. Admittedly, when folks reach out to Sales and ask to buy Plaid and are told they're not eligible because they're not a business, this nuance is sometimes not communicated very well (or at all). We're working on it. :-)
In fact, we actually just this week launched a new sign-up flow to make it waaaay easier for non-businesses to use Plaid, so try checking it out -- after you go to dashboard.plaid.com and create an account, you should see a "Free trial" button show up on the homepage with a link to use the hobbyist onboarding flow.
Correct, sales encourages you to sign their minimum contract, which basically gets you better support and an account manager. Pay as you go is an option, but Plaid indicated you basically wouldn't have any guaranteed support SLA post-launch if you were on PAYG.
Thank you for the info! Is this a somewhat recent change or has it always been this way? "A couple years ago" in my comment was doing some heavy lifting, I probably reached out around 2017ish.
Dear company who has extensive military contracts and is founded in stealing data from people here is every single financial transaction I have ever made! Please don't use it for surveillance pricing tee hee.
At least apple credit cards give you money for that rather then the other way around.
My spouse was almost scammed out of 25k the other day, by a person. There is no way in fucking hell I'll let an "agent" touch my finances. That is madness.
And I totally hear you -- we had this happen in our family as well, and it was really sad. Security is a massive priority for us, but it's always going to be a cost-benefit analysis for each person.
Happy to share more about our infra in a follow-up post.
Actually, it's deterministic -- our product doesn't move money, so when the user gives us access through Plaid, we're only getting read-level permissions. We actually don't even get full account numbers.
A company working with Plaid has to request separate product "scopes" through Plaid in order to be able to move money.
I'm not that familiar with Plaid, but if it works like Yodlee, users have to hand over their credentials so there's no real security, it's just that their scraper is designed to be look not touch.
Plaid has OAuth-based access for most of the big institutions now, but yes, for smaller institutions, they do scraping. Thankfully, Plaid's been around for a while now and has a good track record. It would be a non-starter to give your credentials to a small startup directly.
From there, Supabase MCP or psql gives Claude/Codex access to the transactions/balances for english queries. Really impressed with their ability to find subscription patterns, abnormal patterns, etc. Also to predict cashflow which no online tool so far is good at i.e. "tell me how much cash I can move to savings based on my monthly spend patterns and available cash".
For autocategorization, I learned Claude is really good at custom DSLs. Had it create a markdown table based ruleset to normalize payee/categories. I also run the autocat rules as part of the GitHub actions.
I'm doing something similar with Tiller (which I've been using since Mint was acquired by Intuit).
It's neat to see how OP did this using a Claude Routine though. My version locally uses a local qwen model + an API key (annoyingly created using OAuth) with sheets access. A Claude Routine would've been significantly easier
They have an api and I got llm to write a CLI for it.
That way agent can pretty much pull the data it needs or wants.
One thing I also had it do is build up a series of rules for tagging which then I run a cron for once a day.
Every once in a while I just ask it to look over the rules and make new ones for uncategorized transactions.
(As a side note I think having LLM “memoize” a task through a rule engine or code is really nice pattern)
But once you have the cli with query you can pretty much ask the agent to do anything.
I don't quite understand the desire to have these verbose summaries that you have to read from LLMs. You'll notice anomalies if you just categorize each of your expenses every so often (easy with Tiller).
I actually built it for myself initially, and my wife. So I just built what we needed/wanted.
There will be a huge variety of products in this space and ours is just one take on the problem. I love seeing anything that's taking a shot at it.
It's the ease by which LLMs can ingest and combine various data sources.
I recently needed to set up some calendar events on certain dividend days, but of course, didn't know what those dividend dates actually were. So we used the MCP connector to retrieve our current Vanguard holdings, had GPT-Pro do web research to pull all the dates, and then created calendar events from that. Worked well.
When I'm dealing with my finances the 95% time Claude is correct and doesn't hallucinate is not enough as I have to be vigilant and review its work all the time. So it kinda makes it worthless in this case for me
I don’t understand how anyone is OK with this. It goes against every security principle and it’s against the terms and conditions of every bank.
I realize that almost no bank provides a secure and proper API to get info and/or to transfer funds, but Plaid’s solution is a disaster waiting to happen.
When we built our Plaid integration it used OAuth and a redirect. Plaid just got an access token, you enter your user/pass on the bank site.
Edit: Seems like smaller banks are probably the ones that won't support OAuth. We didn't support those.
The problem is that there sort of isn't a better way right now in the US, and for now, Plaid or a Plaid-like competitor is the safest way. Eventually, it would be awesome if there were clean, open APIs, and standards around this, but for now, it's the best we have.
The alternative of course for the DIY-er is some sort of browser automation, which honestly, is what I tried first. I really wanted it to work, but it didn't - which led us to Plaid.
Now for the criticism: back in the day mint.com was mind-blowing. It's what you always thought you'd wanted. The graphs were interactive and pretty and you really loved seeing them go up. Not so much down. I was so attached to the gamified aspects, much like step counters. They reinforce habits.
My mint journey ended with roughly 5 years or so of data, once they sold to Intuit, didn't like the ads and willingly syncing all my data to mega-corp. Much like Duolingo, it felt good at the time, but I don't know that it did anything for me at all.
Tracking is a double-edged sword: it really does build better habits. It's better to track weight every day for example so you better understand that fluctuations are mostly noise. The daily tracking stuff is entirely useful to get the need to track daily out of your system.
TLDR: checking my net-worth daily sounds like something I should coach myself out from. Ironically that probably takes tools, but the end goal is to not need them.
- We have a built-in CSV export tool in beta right now for cash transactions, and plan to add this for other datasets as well. You should be able to download your data when you want it. It's yours.
- Yes, tracking is great, but it also has a dark side. My sort of vision, at least for what I want, is less of a gamified finance tracker and more of an ambient, always-on agent that's watching for me. It knows my preferences, it knows what I care about, and it tells me when it finds something.
- Before we get there though, for now, it's really interesting to sort of tinker and build your own custom finance automations. As a programmer, it just feels liberating to get the data out of some closed banking app and into a space I'm comfortable in.
- Especially from an investing standpoint, it's been neat to pair our MCP with a much smarter model like 5.4 Pro and have it do long-horizon research tasks that require a lot of web research and correlation.
Quote of the week for me. well said.
~15 years ago I fumbled around with web programming basically because I never learned how to use excel in school. Nerded out with css, html, forms, then php and mysql to script together an unbelievably worse version of what a spreadsheet could do, but it was incredible that I could build something entirely made for my idea. And with the power to improve it.
Thank you for writing and sharing your story, it's motivating and comforting even. Good luck!
For the non-Plaid assets eg., home, car, etc., we just added custom asset MCP tools so you can manually add those and they're included in your computed net worth.
Just this morning, we stood up a demo email agent (basically, email back and forth with Claude with our MCP server connected, providing the data) and it's strangely comforting to chat with it. There's something about the medium of email and how it just works because that's where you're already used to talking with your financial advisor.
There's a lot of nuance in how it's built though, and everyone has different preferences, so to start with the focus is really on building an agent-friendly MCP.
Actually, as part of publicizing our new hobbyist-friendly onboarding, we're looking to work with hobbyists who have created Plaid-powered apps and would be interested in making a short video about their app and their Plaid experience to potentially be featured on the Plaid blog -- if you're interested, shoot me an email at ahoffer@plaid.com and I can send you the details.
In fact, we actually just this week launched a new sign-up flow to make it waaaay easier for non-businesses to use Plaid, so try checking it out -- after you go to dashboard.plaid.com and create an account, you should see a "Free trial" button show up on the homepage with a link to use the hobbyist onboarding flow.
Dear company who has extensive military contracts and is founded in stealing data from people here is every single financial transaction I have ever made! Please don't use it for surveillance pricing tee hee.
At least apple credit cards give you money for that rather then the other way around.
And I totally hear you -- we had this happen in our family as well, and it was really sad. Security is a massive priority for us, but it's always going to be a cost-benefit analysis for each person.
Happy to share more about our infra in a follow-up post.
A company working with Plaid has to request separate product "scopes" through Plaid in order to be able to move money.
I seriously hope this doesn't happen by the way but yea. This is not for me.