741 karma · joined February 17, 2011
I moved to San Francisco on February 1st 2011 with a desire to build a better Internet. I'd like to think I'm making progress.
- LLMs are good enough to zero or few-shot most business questions and assignments, so n.questions is low VS other tasks like writing a codebase.
- Form factor (biased here); maybe threads-only aren't best for business analysis?
Sourcetable is building an AI spreadsheet for the next billion users, both human and AI. We are leaders in autonomous spreadsheets, and you'll be working on fun stuff like this:
https://blog.sourcetable.com/sourcetable-launches-worlds-fir...
Spreadsheets are one of the few 1BN+ user platforms. Come build the future with us.
AI is a platform shift. One spreadsheet will emerge as the new hub for 1bn+ people and their data. That spreadsheet is Sourcetable.
We're playing with agents, autonomy, COT, all popular closed & open source models, and growing fast.
Experienced team, top-tier investors, massive upside. Sound interesting? we're hiring.
Shoot me an email: eoin@sourcetable.com (founder)
I do find it is best when combined with other capabilities so the internal reasoning is more "if Computer Use is the best for solving this stage of the question, use Computer Use. Otherwise, don't.", instead of full Computer Use reliance. So e.g. you might see it triggered for auto-formatting but not writing SQL.
Will report back how it compares vs Operator CUA once we get access!
We're building an AI spreadsheet and application platform for the next billion people. We are most commonly compared to Sheets/Gemini and Excel/Copilot, or referred to as "Cursor for Spreadsheets".
If you are an excellent full-stack engineer (React/Python) with good product sense and experience building hard things, please come talk to us. Most of our team are ex-founders, and there is an expectation that you can build end-to-end without requiring assistance from others. AI experience is nice but not required, this is a product engineering role.
There's a platform shift underway. Let's get after it!
eoin@sourcetable.com
We have an Excel-style reporting interface which is useful the non-technical team members doing operations-style work and analysis. If you like, you can also just write SQL too.
Excel and Sheets cannot do that.
More homepage iterations to come, but the latest one 5x’d conversion of homepage-to-product-demo!
If you are excellent at what you do and have a good sense of humor, please apply!
Sourcetable is building an AI spreadsheet & data platform.
We came out of stealth via ShowHN last two weeks ago: https://news.ycombinator.com/item?id=41590682
5 of 8 on the team are ex-founders and 4 of us have previously founded an AI or ML company. Everybody is technical. We're looking for a staff level eng to join our team in SF. Previous founding-team experience strongly preferred (but not required).
https://sourcetable.com/jobs eoin@sourcetable.com
Anyway, fun fact: it turns out our domain used to be a scam erectile pills website!
One under-discussed feature of fast databases is that they are especially necessary in an agent-centric world. E.g. if you're running recursive SQL to pathfind towards an answer, it has to happen with minimal latency otherwise you break the user experience. Our interface looks like a spreadsheet and users mentally benchmark against spreadsheet-latency speed. They won't accept 20 second query response times they might get from their data warehouse.
We don't yet have enterprise-grade data permissioning or compliance certificates like Soc2. Those will come in time.
Technically you can combine these, but it’s a cumbersome experience and difficult for most people. Vertically integrating their equivalents simplifies things a lot.
(Small note: we don’t currently offer Python to users but likely will at some point)
Very much appreciate the bug report. Thank you!
Curious what will happen if you modify the question to be more explicit?
I have seen that PMs and data-trained folk tend to be very articulate in asking for exactly what they want and that tends to lead to significantly better LLM responses.
TL;DR, most technical people massively overestimate the technical / data abilities of regular spreadsheet users. We find simple use cases are best, and with each new LLM release the UX around more complex data improves significantly.
The reason we chose to build as a full-blown spreadsheet instead of just a table-based solution was that we saw that most people want the flexibility of a regular spreadsheet, but access to their (structured) business data. Table-based solutions wedge you into AI and you can never get out of that.
Insert it as a table on the page (you should see a button), it will then print the whole table result from that query into the spreadsheet. Also, you can check the SQL first and validate it, then print to table after that.
Try a few million rows and see what happens!
Small plug for the analytics tracker we are using which Andrew (CTO) built and is open source: https://github.com/sfproductlabs/tracker
My personal use case tends to involve a lot of Postgres data and transaction events for my reporting. We see "simple" businesses like parts manufacturers, print shops, vineyards, etc. all doing something similar.
Strong note here that the current state of technology is much better for SMB scale data and not enterprise scale data with messy schemas.
Many other advantages of this data centralization too. Data + spreadsheets + compute is a nice application base for agents.
(p.s. I think Andrew, CTO, is going to jump in here as he has more experience in this space.)
And yes! We're definitely of the opinion that as a startup we can outcompete the two trillion-dollar death stars when it comes to product experience. AI is a platform shift!