/

/

Slack

Slack

Costory for Slack

Your FinOps agent,

in your Slack channels.

The agent posts where your engineers already work. It opens an investigation thread when spend moves, pings the owner with the likely cause and a proposed fix, follows up until it’s resolved, and sends every team its weekly showback.

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

Search Acme
G
Acme ▾
▾Channels
finops
team-checkout
team-data
incidents
▾Direct messages
Maria Pavla
▾Apps
Costory
team-checkout▾
Checkout services · cost alerts and weekly showback from Costory
9
Today
CostoryAPP3:12 AM
Cost anomaly · Checkout · Amazon RDS +38% vs 14-day baseline
Likely cause
Deploy checkout-api v4.18 (01:47) changed the primary to db.r6g.4xlarge
Owner
@maria.pavla · Checkout team
If unchanged
≈ €1,900 more this month
Proposed fix
Revert the instance class, or mark as expected if the load test continues
View detailsMark expectedSnooze 24h
3 repliesLast reply today at 9:41 AMView thread
Message #team-checkout
Threadteam-checkout✕
3 replies
Maria Pavla (Checkout)8:55 AM
Leftover from last night’s load test. Reverting now.
CostoryAPP9:41 AM
Spend is back to baseline since 09:30. Closing the thread and logging the event “RDS class revert” on the cost timeline. It will appear in Monday’s showback.
Reply…

What the agent does in Slack

From the first signal

to the closed thread.

Every message has an owner, a likely cause and a next step. Your team decides; the agent keeps track.

Every message has an owner, a likely cause and a next step. Your team decides; the agent keeps track.

01

Opens investigation threads

When a team’s or service’s spend leaves its baseline, the agent posts the change with the likely cause: a deploy, a config change, a usage jump or a provider event.

02

Pings the owner

Ownership comes from your Virtual Dimensions, so the thread lands in the owning team’s channel and mentions the people who can act.

03

Proposes the fix

Revert, rightsize, add a lifecycle rule, change a model route: a concrete next step with the evidence attached.

04

Follows up until resolved

It checks spend after the fix ships and closes the thread when it’s back to baseline, or nudges again if it isn’t.

05

Posts weekly showback

Each team gets its own report in its own channel, with top movers versus last week and what drove them.

06

Sends budget and anomaly alerts

Alerts on actual or forecasted spend post to the channel you choose, for example #finops or #team-data.

Weekly showback

Every team sees its own costs,

in its own channel.

Reports are scoped per team, so nobody scrolls past other teams’ numbers. Pick daily, weekday, weekly or monthly, and the channel for each report.

Anyone in the channel can reply in thread to ask why a line moved, compare periods or get a breakdown by service, without a Costory login.

Search Acme
G
Acme ▾
▾Channels
finops
team-data
team-ml
▾Direct messages
Leo Martin
▾Apps
Costory
team-data▾
Data platform · weekly showback every Monday 9:00
11
Monday
CostoryAPP9:00 AM
Weekly showback · Data platform · €18,420 (+6%)
Top mover
BigQuery +€640 after PR #2291
Down
Dataflow −€210
Next step
Partition orders_daily. Owner: @Leo Martin
2 repliesLast reply Monday at 9:14 AMView thread
Message #team-data
Threadteam-data✕
2 replies
Leo Martin9:14 AM
@Costory what would partitioning save?
CostoryAPP9:14 AM
About €580/week at last week’s run frequency. I’ll check after your next deploy.
Reply…

Setup

Three steps,

a few minutes.

Slack works on top of your Costory workspace. No agent setup is needed for alerts, threads and reports.

Slack setup guide

01

Connect Slack

Add the Costory app to your Slack workspace from Costory’s settings.

02

Invite the bot

Invite @Costory to the channels it should post in: #finops, each team’s channel, #incidents.

03

Choose what goes where

Map teams to channels and pick alerts, investigation threads and report schedules for each.

Slack playbooks

Playbooks that run in Slack

Each one has a trigger, an agent routine and a decision for your team.

Each one has a trigger, an agent routine and a decision for your team.

Costory notices

Every Monday at 9:00, for each team.

Weekly showback per team, posted in each team's Slack channel

Every engineering team gets its own weekly cost report in its own Slack channel, scoped to the services it owns.

Costory notices

Daily, as Datadog usage and the EKS bill refresh.

Dynamic cost reallocation for EKS using Datadog usage

Split shared EKS cluster costs across teams in proportion to what each team's workloads actually use, measured in Datadog.

Costory notices

A shared service's cost grows, or a new team starts using it.

Split shared infrastructure costs by actual usage

Allocate shared databases, networking and platform services to the teams that use them, based on real usage metrics.

Costory notices

A shared API or platform bill lands without an owner.

Split shared API costs across teams with usage data

Allocate untagged or shared API costs, like a single LLM key or a shared data platform account, to teams based on actual usage.

Costory notices

Every day, for every cluster and namespace.

Kubernetes cost allocation by namespace, team and workload

Break EKS, GKE and AKS costs down by cluster, namespace and workload, and roll them up to teams.

Costory notices

The unallocated bucket grows above your threshold.

Allocate cloud costs without perfect tagging

Map accounts, projects, resource names and partial tags to teams with rules, instead of waiting for a tagging project to finish.

Costory notices

Weekly, or when untagged spend jumps.

Tag coverage audit: the agent finds allocation gaps and drafts the rules

Find which label keys could become dimensions, how much spend each one covers, and where untagged cost is concentrated.

Costory notices

A new account, project or cluster appears in billing.

Split production and non-production costs automatically

Allocate every cost line to prod, staging, dev or sandbox using account names, projects, clusters and labels.

Costory notices

Every week, across every connected provider.

One showback across AWS, Google Cloud, Azure, AI and data platforms

Teams see all their costs in one place, whatever the provider: cloud, Kubernetes, data platforms and LLM APIs.

FAQ

Costory in Slack: questions

Which channels can Costory post to?

Any channel you invite the Costory bot to: a central #finops channel, each engineering team’s channel, or an incidents channel. Each report or alert has its own destination.

Do people need a Costory account to use it in Slack?

No. Anyone in the channel can read reports and alerts and reply in thread. Costory accounts are only needed to open the underlying dashboards.

Does the agent change anything in our cloud?

No. It has read-only access to billing data and the metrics you connect. It proposes fixes and tracks them; your team makes the changes.

Do we need Claude or another agent for Slack?

No. Alerts, investigation threads and reports work from Costory directly. Connecting Claude Code or another agent through the Costory MCP adds deeper investigations and optimization work from the terminal or chat.

Put Costory’s agent in your Slack this week

Connect in under 30 minutes, get your first optimization recommendation the next day. 30-day free trial. Copilot, €250/month, with Slack included.

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