The control station, in brief
This station sits between your agent and the tool. Before any call, it checks who is acting, shows only the useful tools, applies the rules below and keeps track of the task.
It can
- List buckets
- Read objects
- Read logs
It asks a human for
- Nothing in particular
It never has access to
- Delete an object or a bucket
Scenario Replays
An agent works through the station. Simulated scenarios, no real data, no key required.
Copy the station, change a limit or an approval step in its configuration file, and get your own station.
The configuration in detail
Everything the station does fits in this file. The replay above applies it, and a copy starts from it. The values are examples to adapt, not a recommendation.
station:
id: aws
kind: product
policies:
- {policy: read-only, at: submit}
global:
language: en
timezone: Europe/Paris
apis:
- id: aws-read
operations:
listBuckets: {access: read}
getObject: {access: read}
readLogs: {access: read}
# not listed, so not available to the agent:
# deleteObject, deleteBucket
profiles:
reader:
allow: [listBuckets, getObject, readLogs]
policies:
read-only:
type: rule
when: "access == write"
effect: deny
reason: "This station allows no writes."
skills:
- {id: list-buckets, uses: listBuckets}
- {id: get-object, uses: getObject}
- {id: read-logs, uses: readLogs}
playbooks:
- id: investigate-an-error
tasks: [read-logs, get-object]Shared copies
Copies that their authors choose to share will appear here. Each one keeps a link to this original station.