How do you run A/B split tests or experiments on your sites?

Please share how you're currently running experiments on your sites. E.g.:

• What software you're using
• Whether you build experiments in JS, backend code, WYSIWYG or CMS UIs
• Who typically manages this process

I'm curious to learn how other developers and organisations run experiments because we're building an open source split testing stack, called Mojito. It'd be useful to know what sort of features and use cases are common to target!