Browser agent
A browser agent is an AI system that operates a web browser autonomously to complete tasks: navigating, reading pages, filling forms, and clicking through flows on behalf of a user or another system. Browser agents are software users, and observing their sessions raises the same recording questions human sessions do, with stricter fidelity demands.
How it works
Browser agents typically run on automation infrastructure (Playwright, Puppeteer, or hosted browser platforms) with a model choosing actions from page state. Their failures depend on the exact state of the page, such as a run encountering an unexpected cookie banner. A DOM-level recording can show how that state changed during the run. Recording is simpler when the agent operates only in a controlled test environment with synthetic accounts and data, because the recorder can be injected into every session. Agents that access real accounts, personal data, or third-party pages still require privacy, authorization, retention, and access-control decisions. Agent sessions are often machine-paced and numerous, which favors compact structured recordings over video.
Where you encounter it
Agent products and internal automations, browser infrastructure platforms, and debugging workflows for browser agents.