Live data from Hacker News

Show HN: I made a free tool that analyzes SEC filings and posts detailed reports

signalbloom.ai

1–10 of 93 posts

Show HN: I made a free tool that analyzes SEC filings and posts detailed reports

#1
(* within a few minutes of SEC filing)

Currently does it for 1000+ US companies and specifically earnings related filings. By US companies, I mean the ones that are obliged to file SEC filings.

This was the result of almost a year long effort and hundreds of prototypes :)

It currently auto-publishes for 1000 ish US companies by market cap, relies on 8-K filing as a trigger.

e.g. https://www.signalbloom.ai/news/NVDA will take you to NVDA earnings

Would be grateful to get some feedback. Especially if you follow a company, check its reports out. Thank you!

Some examples: https://www.signalbloom.ai/news/AAPL/apple-q1-eps-beats-desp...

https://www.signalbloom.ai/news/NVDA/nvidia-revenue-soars-ma...

https://www.signalbloom.ai/news/JPM/jpm-beats-estimates-on-c... (JPM earnings from Friday)

Hallucination note: https://www.signalbloom.ai/hallucination-benchmark

Show HN: I made a free tool that analyzes SEC filings and posts detailed reports
signalbloom.ai

Re: Show HN: I made a free tool that analyzes SEC filings and posts detailed reports

#4
I was thinking of building exactly this type of thing here. This is great and I love the simple/minimalistic styled pages.

Things I was also contemplating to implement you can freely steal:

1. Giving a list of potential interesting investments - these could also be behind paywall.

2. Summarize based on sectors to see where there's downturns coming - again maybe paywall this

3. Connect with news-sites or twitter etc.. to see what is happening and what is the sentiment. This is a lot harder as you'll need to either scrape or pay to get that info.

Best of luck

Re: Show HN: I made a free tool that analyzes SEC filings and posts detailed reports

#7

I was thinking of building exactly this type of thing here. This is great and I love the simple/minimalistic styled pages. Things I was also contemplating to implement you can freely steal: 1. Giving a list of potential interesting investments - these could also be behind paywall. 2. Summarize based on sectors to see where there's downturns coming - again maybe paywall this 3. Connect with news-sites or twitter etc..…

Really nice of you to encourage, thank you! I've thought about some of those.

The first one is an interesting idea, but offering any real financial advice is regulated, which is a tread carefully territory

Second one is achievable and a good one at that. In fact, there is a lot of canonical data out there that when used carefully can provide a very nuanced picture of the current state of economy.

Third one, currently I have just a twitter account where the earnings reports are auto posted the second they are ready (that is, until I run out of free api limits). Their API cost for at the higher end makes it only viable if I am doing it full time and there was a clear edge by analyzing the data. My gut feeling is, most of the work will go into filtering out low signal posts idk

Re: Show HN: I made a free tool that analyzes SEC filings and posts detailed reports

#9
It’s nice, I like it.

PS if the next question is whether I’d pay for it, the answer is likely no ;)

A suggestion: I forget the HTML tag off the top of my head, but there is something you can do that turns off the keyboard autocorrect. Setting the search box input type to something specific or something like that… stock tickers aren’t dictionary words :)

Re: Show HN: I made a free tool that analyzes SEC filings and posts detailed reports

#10

Any pointers on creating similar tools? I had an idea for an AI-backed analyses tool (not for stocks) but not quite sure how to go about it. Even if it's just a pointer to some page that does an ELI5 I'd really appreciate it.

Depending on how much time you have, the first thing I would recommend is to watch Karpathy's 'deep dive into LLMs' video (https://www.youtube.com/watch?v=7xTGNNLPyMI). It is 3.5 hours but it will give you so much instinctive understanding of how these things work and will likely save you a lot of time.

Purely from a technical standpoint, things aren't that difficult really. I'd recommend get yourself an API account with all major providers (because each frontier LLM evidently has their own strengths and weaknesses) and start experimenting with your data. The feeling you'll get when you first get an API response will keep you going! :)

Having said that, a caveat is, LLMs do hallucinate from time to time. If your data needs accuracy, definitely don't do the "throw everything at LLMs and let them do the work" but I'm sure you'll figure it out from trial and error. Good luck!

Post reply on HN