Find candidates for newer instance generations and Graviton
Use the compute metadata in your billing data to list older instance families by owner and estimate the impact of upgrading.
Runs in
Claude · Slack
First optimization recommendation
The next day
ROI
Pays for itself with the first recommendation you act on
How much do we spend on previous-generation EC2 instance families, by service and owner?
€21,400/month runs on m5/c5/r5 families. Top candidate: ingestion-workers (Data) on 24× c5.2xlarge. c7g.2xlarge has a lower hourly price; check ARM compatibility of the native image library first.
Teams plan the migrations that make sense for them.
Playbook
What the agent does
From what Costory notices to what you decide. Costory suggests the next step in conversation, and you decide whether to go ahead.
Costory notices
Monthly review of spend on older instance families.
Costory investigates
01
Read compute metadata
Costory enriches billing rows with compute metadata such as instance family.
02
List candidates
Spend on older generations by service and owner.
03
Add context
Recent deploys and the runtime constraints your team knows about.
04
Prioritize
Claude ranks candidates by impact and effort.
Where you see it
Claude
You decide
Teams plan the migrations that make sense for them.
Why it matters
Older instance generations cost more for the same work. Teams know they should upgrade, but not which services to start with.
Who it’s for
Platform engineers, engineering managers
Where it runs
Claude · Slack
What you get
What lands in front of your team
A ranked upgrade list
Where newer instances matter most.
Owner-ready
Each candidate has a team attached.
Effort-aware
Claude flags known constraints.
Sources and assistants
What it connects
Example prompts
Or drive it yourself
List
How much do we spend on previous-generation EC2 instance families, by service and owner?
Prioritize
Rank the top 10 services to move to Graviton by monthly impact, and flag any that may depend on x86-only components.
FAQ
Questions about this playbook
Does Costory guarantee savings?
No. The agent investigates and recommends with the evidence attached; your team decides what to change. Impact figures are estimates based on your own data.
How long does this playbook take to set up?
Connecting your billing data and the Costory MCP takes under 30 minutes with Terraform or CloudFormation. The playbook itself takes minutes: pick the scope, the trigger and the Slack channel. The first billing data lands the next day, and the agent starts from there.
Can we adjust what the agent does?
Yes. You choose the trigger, the scope (team, service, environment), the channel and the format, and you can pause or change it at any time.
Does Costory change anything in our cloud accounts?
No. Costory reads billing exports and the metrics you connect, and has no write access to your cloud. Actions it takes create Costory objects only: alerts, reports, dashboards and events. Your team stays in control of every change.
Step-by-step guide in the Costory docs
Related playbooks
Run these alongside it
Costory notices
A service runs well below its capacity for 30 days.
Rightsizing recommendations grounded in real usage
The agent compares what you pay for compute with what services actually use in CloudWatch or Datadog, then recommends instance sizes to the owning team, with the deploy history attached.
See the playbook
Costory notices
Coverage drops, or the steady on-demand baseline grows.
Savings Plans and Reserved Instances coverage review
The agent watches covered versus uncovered spend and utilization, and recommends where additional commitments could make sense as your steady baseline grows.
See the playbook
Costory notices
An optimization is logged as shipped.
Measure the impact of every optimization you ship
Log each optimization as an event and compare cost before and after, so the team can show what each change saved.
See the playbook
Put this playbook on call
Included in every plan, from €250/month. 30-day free trial: connect in under 30 minutes, get your first optimization recommendation the next day.
First optimization recommendation
The next day
ROI
Pays for itself with the first recommendation you act on
Setup
About 30 minutes
Data residency
EU
Access
Read-only on your cloud