What it does
You name the use cases you want run, with any scoping — regions, tag keys, thresholds. It scans the connected account and returns findings ranked by estimated monthly cost impact, each carrying the evidence behind the estimate and a specific step to act on.It runs only the use cases you name. A prompt that names none gets the list back rather than a full
scan — deliberately, because a blind scan of every use case across every region is the slowest
possible way to start.
The preflight
Every run, regardless of which use cases you chose, first checks whether the account’s opt-in cost and data features are enabled — Cost Explorer, Cost and Usage Reports, VPC Flow Logs, Cost Anomaly Detection, Budgets and Compute Optimizer. This is not optional, and it is worth reading before the findings. Several use cases are blocked or degraded without those features, and a thin result is much more often a disabled feature than a clean account.What it reads
Read-only, across the services the analysis needs: Cost Explorer, CloudWatch, S3, EC2, EBS, RDS, ELB, EKS and the tagging APIs.Before you deploy
The AWS connection offers the same two authentication modes as the AWS investigator, and which you
see depends on where the agent runs:
Ask it for
In chat, or as a run’s prompt:Defaults and limits
This agent’s budget starts at its maximum rather than below it. A real multi-region account needs
the full window for even one use case, so there is nothing to gain by asking for more — scope the
run by naming fewer use cases or fewer regions instead.
In a workflow
It is a scheduled analysis rather than an incident specialist: give it a trigger, point it at one account, and let the findings accumulate where someone reviews them. Where you run it across several accounts, deploy one per account so each run’s findings carry an unambiguous owner. See Triggers & schedules and Cloud optimization.What it will not do
It finds waste; it never acts on it. There is no mutating tool in its surface, so it cannot stop an instance, delete a volume, change a tag or buy a reservation. Every finding is a recommendation for someone else to carry out. It is also bounded by the preflight: where an opt-in feature is disabled, the analyses that depend on it are degraded or unavailable, and it reports that rather than estimating around the gap.Next steps
Cloud optimization
The module that turns these findings into tracked work.
Triggers & schedules
Run the analysis on a schedule.
AWS Infrastructure Investigator
The same account, read for incidents rather than waste.
Agent catalog
Every catalog agent, side by side.