Skip to main content
Ask your AI agent for a full inventory of everything you run on Runcrate. It lists every resource, calculates costs, identifies waste, and suggests optimizations.

”Give me a complete audit of everything running in my workspace.”

The agent inventories all resources:
  1. list_instances: all GPU instances
  2. list_volumes: all storage volumes
  3. list_environments: all environments
  4. billing_balance: current credit balance
  5. billing_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:
  1. ssh_execute on each instance: checks GPU utilization
  2. list_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:
  1. delete_instance: terminates old-benchmark
  2. delete_volume: deletes temp-scratch
  3. billing_balance: checks updated balance after refunds
Cleanup complete:
  • Terminated old-benchmark (idle 9 days), which stops its hourly billing
  • Deleted temp-scratch (100 GB, eu-central-1): unused credits refunded
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.

Tools used in this workflow