Wispr Flow: Dictation That Works EverywhereStop typing. Start speaking. 4x faster.
Promoted
Jupid
File your taxes with Claude Code
1.1K followers
File your taxes with Claude Code
1.1K 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.
Orchestra
Congrats, team! How often does the bank data sync?
@sergiepoe We work through Plaid, so the sync frequency is basically what Plaid supports. Plaid promises something close to real time, but of course we depend on them, so it isn’t truly real time. Still, it updates often enough to keep your transactions under control.
Interesting approach to Schedule C categorization. Curious — how do you handle the edge case where a freelancer receives payment in crypto (e.g. USDC invoices)? That creates both income recognition AND a cost basis tracking problem downstream.
The "remembers forever" angle is what most tax tools miss. They forget your custom rules every January. How does Jupid handle new vendors mid-year — ask you, default to a category, or wait for you to label?
Loki.Build
Cool release! Is it safe to use?
@nikita_40in Thanks, Nikita! It's quite safe — we've completed SOC 2 certification for data storage and handling.
I saw Kick and Fondo listed as similar products on PH. What's genuinely different about Jupid?
@max_grinevich The biggest difference is where Jupid lives. Kick and Fondo are standalone apps with their own dashboards. Jupid works where you already are - Claude Code, ChatGPT, WhatsApp. No new interface. The second difference is the persistent memory layer: Jupid remembers every vendor relationship forever, which is why accuracy stays high at scale instead of degrading like raw LLM approaches.
As a fellow founder, I felt this pitch in my soul. There are very few things I dread more than opening up a spreadsheet of 500+ bank transactions and trying to remember if a random coffee from six months ago was 'Meals,' 'Office Supplies,' or 'Travel.'
I’ve actually tried the 'dump the CSV into Claude' trick before, and just like you said—by transaction #200, it starts hallucinating and completely loses the plot.
The architectural choice to map memory to the counterparty relationship rather than individual transactions is brilliant. It completely solves the context window problem.
Incredible execution on a deeply painful problem. Huge congrats on the launch, Slava and team!
Jupid
🥰 Thrilled that we are finally live and featured on Product Hunt — right in the middle of US tax season
My favorite feature is working with transactions through Claude Code. If you are a developer who does your own books, this changes everything
First 100 transactions are free to try. And use promo code PRODUCTHUNT for 50% off your first 3 months
Would love to hear what you think — honest feedback means more than upvotes