AI agent has more production access than your senior engineers
There’s a pattern I keep seeing across teams adopting AI agents for infrastructure, and it’s starting to scare me.A team sets up an agent to help with Terraform, Kubernetes configs, or cloud deployments. To make it useful, they give it cloud credentials, state files, sometimes CI/CD pipeline access. They test it in staging. It works. They move it to production. Nobody asks: what’s the blast...