goleary
Joined 13 years ago
Joined 13 years ago
wow
A bit confused by this. If I'm a developer of a PFM, I don't want anything but a single user's financial data synced to their device. This sounds like partial replication to me.
I wrote about how it works here: https://gabeoleary.com/posts/venmo-deeplinking-including-fro...
When I wrote this it only worked on mobile. The deep link would take one into the app with the amount/details etc prefilled out. Just tested and it looks like the same format works on desktop now too.
I had until just now not realized that Plaid has a Venmo integration.
I could imagine using the deep link to begin the transaction and then using the plaid connection to look for it's completion...
I created a tool that helps people stay on top of shared transactions (https://reconcile.app/) a few years ago and have recently been working on another iteration of it that has some similarities to what you've built, but with a focus on couples who share much of but not all of their financial lives.
You can record steps & have the extension replay them on your machine or in the cloud (presumably using puppeteer/playwright).
One idea I had: it would be cool if I could teach the agent. For instance, give it a task, but if it struggles, just complete it myself while the extension observes my interactions.
Perhaps these could be used as few shot examples for priming the model?
Gonna play around with this soon!
My gf uses https://foyr.com once we have the floor plan nailed to get an idea about what colors, textures & furniture to use in a space. It supports higher def renderings. It's kind of expensive though iirc.
They talk about the distinction between reading a book where you have no distractions and no "next" task to move on to and reading on a device - where you are a mere click away from other information & stimulation.
In order to spend actual time reading articles you need to get into a state where you aren't reading to be done with the article and don't care how much time you spend in this state which is pretty hard.
Apps like Pocket/Upnext/Matter/Readwise help, but I find that it takes more than this. People often send their articles to a kindle to facilitate this kind of reading.
One of the key features in Claude Code is "Agentic Search" aka using (rip)grep/ls to search a codebase without any of the overhead of RAG.
Sounds like even RAG approaches use a similar approach (Query Generation).