”Give me a complete audit of everything running in my workspace.”
The agent inventories all resources:list_instances: all GPU instanceslist_volumes: all storage volumeslist_environments: all environmentsbilling_balance: current credit balancebilling_usage: spending over the last 30 days
Infrastructure Audit: May 19, 2026 Instances (4 running):Volumes (3 total):Environments: main, staging, production Balance: $1,247.80 Current burn rate: the four instances above at their live hourly rates, plus storage
”What’s wasting money? Where can I cut costs?”
The agent analyzes utilization:ssh_executeon each instance: checks GPU utilizationlist_volumes: checks for unattached volumes
Waste identified:Potential savings: the hourly rates of old-benchmark and staging-test, plus storage for the two unattached volumes Kill old-benchmark first (idle 9 days), then shut down staging-test between sessions, and delete temp-scratch (wrong region).
”Clean up the waste. Kill idle instances and delete unused volumes.”
The agent executes the cleanup:delete_instance: terminatesold-benchmarkdelete_volume: deletestemp-scratchbilling_balance: checks updated balance after refunds
Cleanup complete:Burn rate: down by old-benchmark’s hourly rate, and temp-scratch no longer bills. Remaining resources: 3 instances, 2 volumes across 3 environments. Next recommendation: shut down staging-test when you’re not actively testing.
- Terminated old-benchmark (idle 9 days), which stops its hourly billing
- Deleted temp-scratch (100 GB, eu-central-1): unused credits refunded