Search for a command to run...
Articles tagged with #ai-agents
We previously examined common approaches teams use to protect production databases (i.e. command allowlists, SQL filters, and manual approval workflows) and why they fail in the presence of autonomous
As AI agents become more capable, teams are trying to limit the damage they can do when given access to SSH or production databases. Common approaches include: Command allowlists: allow ls, cat, grep
Background Context We’re building Pochi, a full-stack AI teammate that can handle all your coding tasks and think, communicate, and work like a real engineer. One of our recent feature requests involved releasing Parallel agents. Most teams rarely wo...
