Describing your servers, databases and networks in files kept in the repo, and letting a tool make the real world match them, in place of clicking around a console.
Changes become reviewable and repeatable. It also means one wrong command can change everything at once. Agents are good at writing these files. The danger is in letting them run the result.
Say it to your agent
“Write the Terraform and run terraform plan -out=tfplan. Show me every line that says destroy or replace. Never run apply and never use auto-approve: I'll apply that saved plan myself. If you can't read the remote state, stop and say so.”