We're rolling out a feature that lets you vibecode Excel models, the same category a well-funded Silicon Valley startup has been getting attention for. Building it out, we realised we don't just match what's currently considered best. We beat it.
Here's our output for the prompt "build a detailed LBO model for ExxonMobil": https://docs.google.com/spreadsh...
Run that same prompt on any other platform and the gap is hard to miss.
Here is what claude had to say about our results vs others:
https://claude.ai/public/artifac...
How we did it: we generate Excel server-side instead of client-side, using openpyxl as the engine. We built on top of it to support pivot tables and everything else a real model needs. The reasoning behind the bet: openpyxl is heavily represented in training data, so the model actually knows how to drive it. That's the difference between a spreadsheet that looks right and one that is right.
The last mile is where all the time goes, so shipping the finished deck instead of a wall of text is great. Looked at the equity report, structure looks great. Nice launch.