“AI agents are quickly moving beyond chat. They inspect code, run tests, read documents, search knowledge bases, query internal systems, and operate for hours on behalf of a user.”

Alex Sandu et al.

“the user’s laptop, browser, integrated development environment (IDE), or terminal serves as the presentation layer, not the execution layer”

Alex Sandu et al.

“In order to govern an agent, you need to define the range of expected behaviors and draw boundaries that prevent unexpected access.”

Alex Sandu et al.

“Require human approval: Ensure any agent action that changes a system (like merging code or updating tickets) must be approved by a human, not just the agent.”

Alex Sandu et al.

“Credential protection: Don’t store passwords or secret keys directly in the workspace. Use a secure proxy that handles those keys behind the scenes so the agent never sees the raw secrets.”

Alex Sandu et al.