Philosophy
Nowadays an agent can build a complete product in an afternoon. But actually shipping it takes more: the platform, the deployment, the operations. With a traditional PaaS, that quickly becomes the bottleneck.
A platform built for humans has checkpoints that need a human: a setting that only exists in the console, a form to fill in, an approval to wait for. That was never a problem before. A team took weeks to build the product, so a few minutes of clicking at the end cost nothing, and each checkpoint landed on a milestone worth celebrating anyway.
An agent works in hours, and the same checkpoints are now the slowest part of the job. They set the pace, and they set it slow.
Agent-native means the agent does the platform work too, all of it, so nothing waits on you. For a cloud, that has a precise meaning: the agent provisions all the services and connects them to each other through the API, with no step that can only be done in a console.
Once you design a cloud that way, two things become obvious.
First, agents work best on Linux, the most standard and open platform there is. More has been written about it than about any other system, so an agent already knows it. A proprietary stack has to be explained to the agent at the start of every session, and even then the agent can only do what the stack allows.
Second, most of what a traditional PaaS sells is redundant. Its queue, its search index, its scheduler and its metrics stack all wrap open-source software that anyone can install. Customers paid for the wrapper because installing it took a week and running it took someone's attention from then on. An agent installs and runs the same software in minutes, so the wrapper is no longer worth paying for.
We sell only the services an agent cannot build for itself, plus a plain Linux machine to build the rest on. Anything an agent can build — observability, an API gateway, a serverless runtime, a queue — we do not sell.
An agent can write software. It cannot conjure hardware, an IP address, or a mail server that other mail servers trust. So we sell a machine with root on it, storage that grows and moves between machines, snapshots, an address, and an outbound mail relay. If we find something else an agent cannot get for itself, we will sell that too — DNS hosting and a second location are the two we are looking at now.
There is a benefit here that is easy to miss. What your agent builds is built for your product alone, not for the average customer, so it is usually smaller and faster than the managed version, and sometimes it does something the managed version could not do at all.
And the cloud gets out of your way. You no longer need to know whether the code runs in a container, how the database is tuned, or how staging differs from production, because you are no longer the one deciding.
Every managed service is a system somebody has to run, and the cost of running it is inside its price. We do not run any of them, so our prices are lower.
Two things: the money and the stop switch. Only you can add credit or change the payment method. Only someone with your authenticator can unfreeze the account. Everything else is your agent's job.