Back to How we built Grok Bot in a month | Roman Ugarte (SpaceXAI), with Roman Ugarte.
How Did a Tiny Team Ship Grok Bot in a Month?
Roman Ugarte says SpaceXAI built Grok Bot from a blank page in about a month, with a handful of people isolated from the rest of the company so they could make micro decisions every day.
The work started completely from scratch. The team already knew how to build great agents for developers and engineers, and the open question was what a product like that should look like for knowledge work. A small group went off into a cave for about a month with one objective: build an amazing knowledge work product that brings agents to the rest of the company. From the first line of code to the internal prototype was only about a month, a quick scrappy build. A much bigger group thinking in a six to 12 month vision would not have reached the place they landed. They sat in a separate part of the office and used private Slack channels. At the end they had a functional, useful product the core team was excited about.
They rolled Grok Bot out across the company, across all of SpaceXAI, at an all hands where they shared the progress and asked people to use the brand new product. The core team was already using it constantly, but it is easy to use the thing you built when you understand the mechanics and what it is good for. The pressure test was whether people would switch from other internal tools and other external tools to use Grok Bot as their primary agent surface. In the first week after the all hands, an outpour of love for Grok Bot came from people and from groups of the company that maybe you wouldn't expect.
How we built Grok Bot in a month | Roman Ugarte (SpaceXAI) ·
From the transcript
It figured out what the hell the last episode was, how to promote it. So I actually remember in the moment being like, wow, this is really good. So let's actually start with the origin story. Where did this start? What was kind of the original idea? And when did the work on this begin?
Yeah, it started... really as a blank page, completely from scratch, build from zero exercise, where I think we'd been feeling for a long time that we wanted to build something that wasn't just a great product for developers and engineers, which is really where we started. And I think we've gained a lot of intuition about how to build great agents and useful products that way.
But what would that product look like for knowledge work? And we decided to kind of create this very small team internally. It was really just a handful of people to go off into a cave for about a month with the sole objective of build an amazing knowledge work product that brings agents to the rest of the company. And I think from the first line of code to when we released this prototype internally, it was only about a month.