mbm

Looks neat! Thanks for sharing. This is going to be a space with many different players, which I personally think is awesome.

Great questions.

On banks not supported by Plaid — while most are covered already (12,000+), totally understand that some like Fidelity aren’t. For this, we’re considering a way to manually import statements, but that wouldn’t support the live data sync that Plaid provides of course.

Performance tracking — yes! Absolutely on this. We’ve been sketching this out lately since it has some nuance to get right. Would love your input on what you’d like to see here.

Nice, thanks for sharing. I’m curious how MX compares to Plaid.

Yeah, investing over time in such a way to beat the S&P is actually incredibly challenging (having tried it myself). I’m very skeptical an LLM can do better than that unless it has a very large, expensive firehose of data.

It may be that more mundane analysis ends up being the most useful. For example — for years, we had some money in a money market fund earning basically no interest. It just wasn’t on the radar.

Had even a not very smart LLM nudged us to put the money into a HYSA earlier, we would have made thousands per year in interest.

My wife also recently used our tool to do some simple investing optimization that’s going to save us a few thousand per year on taxes.

Thing like this aren’t sexy but do have value, and don’t take GPT Pro.

Correct. That’s interesting — so you explicitly opted out for any non-OAuth institutions?

Correct. They’re incentivized to try to make it as seamless and secure as possible for the 95%, but it’s challenging to build custom integrations for thousands of institutions. Wouldn’t open standards be nice?

Hi, just to share - the DevTools experiment was in my initial build for myself, prior to deciding to make it into a product.

Thanks :-)

Now that would be innovative.

hledger is amazing.

Local AI models are getting a lot better. If you have the capability to run them, you could automate this yourself using your own browser automation, actually. It is rather fiddly, as mentioned in the post, but is absolutely doable, and probably the only option, at least for now, where you wouldn't need to provide your credentials to a third party.

Plaid does do screen scraping for smaller banks, but they have agreements for OAuth-based access with most of the largest institutions.

That's so awesome! You should open source this. Wish we had this in the US, would make things so much easier.

The main reason I do it, at least, is because the insights it provides (as someone who's interested in spending patterns/investing/etc.) are actually quite useful. With even a very basic prompt, I've found things that were otherwise completely missed.

Making it secure is actually quite hard, but that's why we're spending an enormous amount of time thinking about that.

Yeah, I actually agree with you -- this is something that needs a ton of guardrails. It'll take a lot of thought to build correctly.

Yes, give it a try! I did this on my own first before deciding to make it "a thing." It's actually a really fun project and gives you a ton of insight into your finances. I'd recommend it.

Hey! Thanks for stopping by. Actually planning to do a full blog post on this topic soon (how to get started with Plaid).

It was a bit of a process involving sales calls, contracts, security attestations, etc., but they're planning to make it easier to try out the platform. There is a pay-as-you-go, developer-friendly option, but the support it includes is pretty flaky. The support issue is less "my code broke" and more things like "this institution isn't returning what it should," or, "I haven't been approved yet by this institution that does manual review."

Overall, it's been a pretty good experience! I'd suggest spinning up an app if you're considering them. Here are their LLM-friendly docs: https://plaid.com/docs/llms-full.txt

Looks pretty good! Give it a try and let us know how it works?

Yup, it would be really awesome if this concept was deployed in the US. Unfortunately, open standards don't seem to gain as much traction here outside of the tech industry.

Have you tried browser automation?

Just to share -- Most of the largest banks/FIs actually work directly with Plaid.

Here's a quick list of some of the major ones:

JPMorgan Chase, Bank of America, Wells Fargo, Citibank, U.S. Bank, PNC, Capital One, Truist, TD Bank, Charles Schwab, Vanguard, Marcus by Goldman Sachs, Goldman Sachs Private Wealth, Morgan Stanley, E*TRADE, USAA, M&T, RBC, American Express, Fifth Third, Citizens, KeyBank, Huntington, Ally, Discover, BMO

Hear you 100%. It's certainly not for everyone, and I respect your position.

Same here -- I mainly use Driggsby from Codex or Claude Code, not ChatGPT or Claude actually.

Thanks for sharing about the apartment -- that's super cool and a really great use-case.

Thanks for stopping by, Alex! Looks awesome -- good luck to you guys!

This is really neat, and actually pretty sophisticated. It's like a tiny fintech.

How well has the cash flow prediction worked?

I respect that 100%. Thanks for sharing your thoughts!

Side note: the Apple Card is awesome. We have it & love it. Would really like to integrate with FinanceKit (Apple's Plaid, basically) to pull in that data too.

The awesome thing is, if it's something you're interested in, you can basically set this up yourself -- a local AI model, some browser automation, and it does mostly work! It's just a pain to keep running. But it's definitely doable.

Thanks. If I could ask, what would interest you?

In case anyone is interested, just wanted to share a few high level details about our infra/security setup.

- Backend & CLI are both strictly linted Rust. The webapp runs on Axum (Rust web framework), and connects to Postgres via sqlx.

- Financial read-only. There's no transfer, pay, or send tool in the product. Nothing in the AI surface can move money.

- We request transactions, investments, and liabilities from Plaid. We don't request auth, transfer, or payment_initiation, so we never receive full account numbers or routing numbers — just the last-4 mask Plaid returns by default.

- Bank usernames and passwords go to Plaid Link, not us. We only hold a per-institution access token.

- Plaid access tokens live in a separate database behind a single custody Cloud Run service, encrypted at rest by Cloud KMS. The broker calls KMS's encrypt/decrypt endpoints — the root key material never leaves Google's HSM boundary and the broker's service account is the only one with encrypt/decrypt permissions. The web app doesn't have permission to read that database.

- Every encryption and decryption call passes the Plaid item ID as AAD (additional authenticated data). A ciphertext from one item cannot be swapped in and decrypted as another item's token.

- Each Cloud Run service (including our web app) runs under its own cloud identity and with its own DB role.

- Internal calls between services are authenticated: the caller presents a short-lived identity token from the cloud provider, and the receiver verifies it.

- The prod databases have no public IP. Secrets live in managed secret storage, not in source or container images.

- The AI connector is OAuth 2.1 + PKCE, scoped per user, revocable from the UI. Every tool call records the tool name, sanitized args, calling client, and the reason the agent supplied, so you can see what your LLM asked on your behalf.

- There are no fetch-URL, shell, or general I/O tools in the AI surface. Tools return structured financial data and nothing else.

- Networking, IAM, and DB grants are all in Terraform. All infra changes go through that path.

- Infra access is gated by 2fa and security keys.

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.