At the GitHub AI Summit, I ran an exercise focused on capacity planning across four teams working on closely related services. Officially, the goal was to ideate how we could better manage our GPU compute capacity. Unofficially, I had a deeper agenda: to reveal just how differently each team saw the system—even though we were all building the same product.

It might sound odd to say I had an ulterior motive, but I’ve seen this pattern everywhere I’ve worked. Even on highly aligned, well-intentioned teams, you’ll often find:
[Read More]