Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
Show HN: I automated forensic accounting for divorce cases (3 min vs. 4 weeks)
6 points by cd_mkdir 5 days ago | hide | past | favorite | 3 comments
Burned about 1 weeks on this. Not sure if it's useful to anyone beyond my original use case, but figure I'd share.

Friend went through a nasty divorce. Had $750k going into the marriage (inheritance), put it in a joint account like an idiot. Five years later, account's been up and down, money mixed with paychecks and mortgage payments. Lawyer says "you need a forensic accountant to trace what's still yours." Quote comes back: $5k, 4 weeks minimum.

I'm sitting there thinking - this is just transaction categorization and some relatively simple math (the "Lowest Intermediate Balance Rule" if you want to google it). Why doesn't software exist for this?

Turns out it kind of doesn't. There are $50k enterprise tools for big law firms, but nothing a normal person or small practice can actually use.

So I built a Django app that takes bank statement PDFs, uses latest Mistral's OCR-3 to parse them (because real-world bank PDFs and shots are a nightmare - scanned, rotated, weird formats), then runs them through an LLM to categorize transactions and a Python implementation of the LIBR algorithm.

Output is a court-usable report showing exactly how much of your "separate property" is still traceable, with visualizations and evidence logging (SHA-256 hashing for chain of custody, audit trails, the works).

Its FREE and whole process takes about 3 minutes. I'm in India and honestly just want to see if people use it.

What's really interesting:

-Latest Mistral's document OCR-3 is genuinely impressive on messy banking PDFs. Tried Tesseract first, got maybe 60% accuracy.

-The LIBR algorithm is conceptually simple but has some gnarly edge cases (what happens when account hits zero? how do you handle multiple deposits of separate property? etc.)

-Evidence integrity was harder than expected. Lawyers care a LOT about proving a document hasn't been tampered with.

-Used Celery because some statements have 10k+ transactions and you can't block the request

Currently running on Render with Postgres. Code's not open source yet because honestly it's kind of a mess and I need to clean up some stuff, but might do that if there's interest.

Things I'm unsure about:

-Should it be free? Subscription? How much? Bring your won key? Cause I'm putting money out of my pocket.

-B2C vs B2B - individuals might use this once, but lawyers could use it repeatedly.

-How much do I need to worry about legal liability for the output? I have disclaimers everywhere but still

Anyway, it's live: https://exitprotocols.com.

Would love feedback, especially if you've dealt with this problem before or know the family law space.





The LIBR logic is straightforward, but OCR quality, auditability, and evidence integrity are what make this usable in the real world.

lawyers care about chain of custody, auditability, and immutability makes this less of an “AI app” and more of a compliance workflow tool, which might matter a lot for positioning.

On B2C vs B2B: individuals feel this once, lawyers feel it every case — which usually determines who actually pays.

The biggest risk seems less about accuracy and more about how courts classify the output (calculator vs expert opinion). That likely drives both liability and pricing.

Have you run this past a practicing family lawyer or forensic accountant yet, even informally?


OP here – thanks for the feedback. I just pushed an update to address the Chain of Custody concerns.

The system now generates immutable forensic reports with SHA-256 integrity hashes for every document. Also added a regression suite to verify the tracing algorithm against known edge cases. The focus is definitely shifting from just "AI wrapper" to "Audit Compliance tool.

Case: https://exitprotocols.com/static/documents/Sterling_Forensic...


I don't have much feedback on the project or space you're in but wanted to note that find this interesting.

I've read mixed reviews about OCR-3. I'm a bit surprised this hasn't been your experience. Many others note Gemini is good at this type of task. Curious how you came to find that OCR-3 was best suited for your needs?

Maybe a 1x payment option or token-based option for individuals who just want to use this service 1x? You could also workshop it with smaller legal firms to see if they'd actually find it useful.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: