When the collateral is a chip: how GPU-backed loans really work A note before we start: the worked example below is illustrative. It uses simple assumptions to show the mechanics, not the terms of any real loan. Issues 03 to 05 were about buildings. A data center is collateral
Issue 04 stress-tested a data center SPV: what happens if the tenant leaves and the building sits empty. That exercise assumed the tenant and the owner are two separate parties. In some of the biggest AI data center financings, they are not. The tenant also owns 20% of the
A note before we start: the numbers below are illustrative. They extend the SPV from Issue 03 and are built to show how a stress test works, not to describe a real company's financials. The point is learning which levers matter. In Issue 01, the claim was that
ISSUE 03 A quick note before we start: the numbers below are illustrative, built to show how the structure works not a real company's financials. The point isn't the figures. It's learning where to look. In Issue 01, the story was that AI data
ISSUE 02 In Issue 01, the story was the US: private credit funds like Blue Owl underwriting data centers against a hyperscaler's lease rather than the building itself. Debt investors don't need to believe in AGI they need to believe the tenant will keep paying rent.
ISSUE 01 Everyone is talking about the $100B+ equity rounds going into AI labs. Almost no one is talking about how the infrastructure underneath them actually gets built. The part that doesn't make headlines: AI data centers aren't being financed like tech startups. They're
This is Capital Matter, a brand-new site by Kaviya Gopal that's just getting started. Things will be up and running here shortly, but you can subscribe in the meantime if you'd like to stay up to date and receive emails when new content is published!