The first programming languages were interpreted, not "compiled".

The first high-level programming language was Plankalkül, created by Konrad Zuse between 1942 and 1945. The first high-level language to have an associated compiler was created by Corrado Böhm in 1951, for his PhD thesis. The first commercially available language was FORTRAN (FORmula TRANslation), developed in 1956 (first manual appeared in 1956, but first developed in 1954) by a team led by John Backus at IBM.

Of course, interpretation doesn't remove the need for compilation entirely, it merely hides some of the compilation from the user.

I'm going to use the term "compiled" here loosely. I'm bundling in preprocessors and transpilers, since to many users, they resemble a build step that's similar to a compile step.

Nearly every language that historically been interpreted is moving compilation steps up the build pipeline and making them user facing.

One consequence of this is that interpreted languages now have compilation steps "bolted-on". You can see this in the clunky user experience to compile Sass to CSS (which requires the OS-dependent libsass) or the slow iteration cycles of JavaScript bundlers like webpack.

Another consequence is that we might need more general-purpose build tools to bring all of these compilation steps together. In the past, you'd compile your program and deploy it. Now, you need to compile multiple parts of your frontend and backend applications. First-generation tools like make aren't sophisticated enough to piece together all of these steps seamlessly.

Some examples of interpreted languages running through a compile build step.

CSS

JavaScript

HTML

Python

Configuration Languages (JSON, YAML, XML, etc.)

Wire formats (protobuf, thrift, etc.)