Launching today
Jupid
File your taxes with Claude Code
779 followers
File your taxes with Claude Code
779 followers
No matter how powerful LLMs get, they are objectively bad at financial transactions. Context loss, inconsistent categories, no memory between sessions. Jupid fixes the data layer. Connect your bank — it learns your business and every vendor relationship once, then remembers forever. Transactions mapped to IRS Schedule C categories (~96% accuracy). Missed deductions found: $1,249/year average. File your Schedule C in 5 minutes. Works with Claude Code. Free trial + 50% off first 3 months.
minimalist phone: creating folders
Just in time!! This day, we have the last day to report our incomes and calculate tax rates. Does it work internationally, or only in the US region for now?
@busmark_w_nika Yes — the Schedule C filing flow is US-specific for now. But the rest of Jupid is not limited to the US: our transaction categorization + context layer works globally, so you can use it to organize transactions, build custom reports, and work with your data in Claude Code or other reporting workflows. So the tax filing form is US-only, but the core intelligence layer is not :)
@slavaakulov How does Jupid "remember" that context long-term without constant retraining, especially for solopreneurs like me juggling multiple clients?
@swati_paliwal Great question, Swati! We don't work with transactions — we work with your counterparties. We build context around your connections with partners, clients, and vendors. So the context is stored around your relationships, not around individual transactions. This keeps the context window very efficient — no need to store thousands of transactions in a single context window.
Sidekick Browser for Teams
@slavaakulov
This is fantastic, after years of IRS fines, missed deadlines and accounting mess (there's always something more important to do in a startup than accounting) having something like is a godsend :) I only wish you guys launched a decade ago )
@dmitry_pushkarev Dmitry, thank you so much for the kind words! Really means a lot. I hope Jupid saves you from those IRS fines going forward
Tobira.ai
@vlad_shipilov Vlad, thank you for the kind words! Hope we'll be useful — give it a try and let us know how it goes!
@vlad_shipilov Same energy here. I think most founders would rather debug a production incident at 3am than open their accounting software. At least the incident has stack traces
Nice launch! I run a single-member US LLC. Most of my expenses are SaaS subscriptions, a few contractor payments, and the occasional travel. Pretty clean Schedule C. Two questions: (1) How does Jupid handle the personal vs. business split on a single bank account — does it learn which recurring charges are business over time, or do I have to tag everything manually upfront? (2) For a low-volume consulting LLC (~50-100 transactions/month), is there enough signal for the categorization engine to be useful, or does this shine more at higher transaction volumes?
@sergey_kalachev Our topmost goal is eventually make it so you don't need to tag anything manually!
think of working with a real human accountant: sometimes he'll have to ask you questions ("Did you fuel your car here for personal needs or business travel?"), but often, knowing you, your company operations, your history and preferences, he can make this assumption on his own.
That's our target: Jupid should become well-versed in your operations so it'll bother you only when it's necessary and just once.
@sergey_kalachev Great questions, Sergey! First, on personal vs. business — we start with the bank account type. Generally, the account itself sets the pattern for how we treat transactions: business expense or personal. You can always override and mark any personal transaction as business. As for transaction volume — it's really just a matter of tokens our system consumes. The categorization question is most relevant during onboarding, when you're just starting out. After that, transactions naturally become more predictable and typed, and volume doesn't matter much.
Banyan AI Lite
Good luck and happy launch! Question: whoch countries do you cover and how do you make sure results are deterministic, no hallucinations or wrong calculation. You know, you better not fool around with tax authorities 😀
@davitausberlin Great question, Davit! Right now we cover the US for tax filing. As for hallucinations — yes, you have to fight them. We've built a multi-layer supervision system with cross-validation between different models, plus manual review checkpoints. You definitely don't want to mess around with tax authorities 😄
@davitausberlin As someone who's seen what happens when you DO fool around with tax authorities... hard agree 😅 That's why we built the validation layer before we built anything else
AgentQL
If our company already considers using one of the alternatives, like Fondo, how are you different from them? Any highlights/number differences?
@colriot Fondo is a great company. But they still rely heavily on manual work for bookkeeping. Where we excel is the technology — you practically don't need manual work anymore. Out of the box, you get high-quality categorization. Plus you always have instant communication with our AI accountant through any messenger.
Skala
This solves a pain I've been feeling for a while. I dumped my bank CSV into Claude last month and it was great at first, but by the 200th transaction it was categorizing Uber rides as 'Office Supplies.' How does Jupid keep accuracy high across thousands of transactions?
@danilakropotkin Great question! Our innovation is that we don't work with transactions directly — we work with your counterparties. When we understand the background and context of who you're doing business with, assigning the correct category becomes straightforward, because the relationship between your company and the counterparty IS the economic essence of the transaction. That's how we maintain high accuracy across thousands of transactions.
@danilakropotkin "Uber rides as Office Supplies" — I'm stealing that for our marketing 😄 But seriously, we've seen Claude categorize the same coffee shop as Meals, then Supplies, then Advertising in the same session. At least it's creative :)