Also called RPA.
Robotic process automation, or RPA, is software that clicks through existing screens the way a person would. It logs in, copies a field, pastes it somewhere else. It does not understand the work. It repeats a script. It was the standard answer before language models, and it still fits when the only way into a system is the screen.
RPA breaks when a button moves or a label changes. An AI step can read a varied document, but the click-script is still brittle. Prefer a proper connection to the system when one exists. Use screen-clicking when it does not, and budget for the scripts to be fixed every time the vendor redesigns a page.
Think of it this way: RPA is a macro that runs at the speed of a robot. It clicks the buttons, copies the data, and fills the forms exactly as a person would, just thousands of times faster and without fatigue.
A healthcare administrator uses RPA to pull patient data from a legacy system and enter it into a new one. The systems have no API bridge. RPA fills the gap without a costly integration project.
A finance team uses RPA to move approved invoices from a portal that has no export and no API. The script works until the portal adds a new confirmation box. Invoices sit unseen for two days. An owner notices because the daily count dropped, which is the check that saved the month-end.
For stable, repetitive tasks in existing systems that have no API. Particularly useful in legacy environments where building real integrations would take years. When the screens or workflows change frequently, RPA breaks immediately and requires manual intervention. It also cannot handle any step that requires reading an unstructured document or making a judgment call.
RaftLabs builds agents that do one defined job, with a person still on the steps that cannot be undone. You see the workflow on your own data before it runs on its own. The related work on our side is RPA services.
This sits with the other agents & automation terms on the glossary. When software stops only answering and starts carrying out the work. Worth reading next: AI Agent, Agentic AI, and Multi-agent System.