> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vantage.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# 30-Day Getting Started Playbook

> An opinionated four-week plan to take a new Vantage account from first integration to a working FinOps cadence.

Built for the FinOps lead, platform engineer, or finance partner who just signed up. Each week maps practical Vantage tasks to [FinOps Foundation capabilities](https://www.finops.org/framework/capabilities/) and helps build a [Crawl-stage](https://www.finops.org/framework/maturity-model/) foundation across the capabilities covered here. The four weeks run in order, but [FinOps is iterative](https://www.finops.org/framework/phases/). Finishing the playbook starts the next loop, not the end of the work.

<CardGroup cols={2}>
  <Card title="Week 1" icon="flag-checkered" href="#week-1-connect-and-see">
    Data Ingestion: Connect and See
  </Card>

  <Card title="Week 2" icon="tags" href="#week-2-allocate-and-report">
    Allocation: Allocate and Report
  </Card>

  <Card title="Week 3" icon="bell" href="#week-3-budget-alert-and-govern">
    Budgeting and Alerts: Govern
  </Card>

  <Card title="Week 4" icon="wand-magic-sparkles" href="#week-4-optimize-and-operate-with-ai">
    Optimization and Enablement: Save with AI
  </Card>
</CardGroup>

Each step links out to Vantage feature docs, [FinOps Foundation framework](https://www.finops.org/framework/) pages, [Vantage blog](https://www.vantage.sh/blog) posts on real customer patterns, the [Cloud Cost Handbook](https://handbook.vantage.sh/), and companion guides like [Scaling virtual tags](/guides/scaling_tagging) and [FinOps as Code](/guides/finops_as_code). Follow them when you want to go deeper than the week-by-week.

<Card title="Use AI to do the work" icon="wand-magic-sparkles">
  Each week below includes prompts you can run in the [FinOps Agent](/vantage_finops_agent) or [Vantage MCP](/vantage_mcp) to do that week's work. Want a saved, refreshable table instead of a chat answer? Run the same prompts in [Canvas](/canvas). See the [FinOps AI Prompt Guide](/guides/finops_ai_prompt_guide) for more patterns.
</Card>

<Note>
  Use this as a baseline, not a fixed implementation order. Commercial or Enterprise teams often move at different speeds based on connected providers, access requirements, business goals, and FinOps maturity. Some teams prioritize unit costs early; others need more time on integrations, allocation, dashboards, or optimization.
</Note>

## Week 1: Connect and See

<div
  style={{
borderRadius: "12px",
padding: "1.5px",
background: "linear-gradient(135deg, #6742D6 0%, rgba(103, 66, 214, 0.3) 50%, #6742D6 100%)",
marginBottom: "1.5rem"
}}
>
  <div
    style={{
borderRadius: "10.5px",
padding: "1.1rem 1.4rem",
backgroundColor: "light-dark(#FDFCFD, #0F1218)"
}}
  >
    <div
      style={{
  display: "inline-block",
  borderRadius: "8px",
  border: "1px solid light-dark(#E6E2EF, #303341)",
  padding: "0.25rem 0.6rem",
  fontSize: "0.875rem",
  fontWeight: 600,
  backgroundColor: "light-dark(#F7F4FF, #171420)",
  color: "light-dark(#4D2EB2, #B8A8FF)",
  marginBottom: "0.75rem"
}}
    >
      Days 1–7
    </div>

    <p style={{ margin: "0 0 0.5rem 0" }}>
      <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/capabilities/data-ingestion/">Data Ingestion</a> capability · primarily supports the <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/phases/#inform">Inform phase</a>
    </p>

    <p style={{ fontStyle: "italic", margin: 0 }}>
      Every dollar of cloud, SaaS, and AI spend is visible in one Vantage account, with at least one workspace and one shared report.
    </p>
  </div>
</div>

<Steps>
  <Step title="Connect Your Primary Providers">
    Connect [AWS](/connecting_aws), [Azure](/connecting_azure), [GCP](/connecting_gcp), or any combination of the three. For AWS, start at the management (payer) account so member accounts inherit. For Azure and GCP, each connection doc covers the right billing scope to start from. Add [Kubernetes](/connecting_kubernetes) via the [agent](/kubernetes_agent) only **after** the underlying cloud provider is connected. Vantage attributes node costs back to AWS, Azure, or GCP.

    Then add the SaaS, data, and AI providers you already pay for: [Snowflake](/connecting_snowflake), [Databricks](/connecting_databricks), [Datadog](/connecting_datadog), [OpenAI](/connecting_open_ai), [Anthropic](/connecting_anthropic), [Cursor](/connecting_cursor), and [GitHub](/connecting_github). Including SaaS and AI from the start, not just IaaS, is the [FinOps Foundation Data Ingestion capability](https://www.finops.org/framework/capabilities/data-ingestion/) in practice.
  </Step>

  <Step title="Wait for Stable Status">
    Watch **Settings > Integrations** until each integration shows **Stable**. See [integration status](/vantage_account#integration-status) for what each state means.

    AWS specifically: granular filtering and grouping by resource and tag require the [CUR](/connecting_aws#cur-format) to be ingested. Set expectations with stakeholders. The first CUR can take up to 24 hours to arrive, so those AWS views won't have full detail at the start. See [AWS Data Ingestion Delay](/connecting_aws#aws-data-ingestion-delay) for what's available in the meantime.
  </Step>

  <Step title="Decide Your Workspace Strategy">
    Read [workspaces](/workspaces) and pick one of two patterns:

    * **One workspace per business unit**: when cost data needs hard separation between groups.
    * **One shared workspace**: when everyone should see everything.

    A [workspace](/workspaces) is a security boundary; sharing a single report is not.
  </Step>

  <Step title="Set Up RBAC If You Need Data Separation">
    If your organization needs hard separation between business units or regulated teams, configure RBAC **now**, before users start exploring. Once people have visibility into cost data, taking it back is politically harder than never granting it in the first place.

    Follow the [RBAC Setup Guide](/guides/rbac_setup) for the recommended pattern: lock down the Everyone team, create dedicated teams scoped to specific workspaces, and assign provider integrations to the workspaces those teams should see.

    <Note>
      Advanced RBAC ([scoped team workspace access](/rbac), [SSO group mapping](/sso#set-up-sso-group-mapping-for-teams)) requires an Enterprise tier account. Single-team accounts and small orgs without separation requirements can skip this step.
    </Note>
  </Step>

  <Step title="Invite Your Team">
    In **Settings > People**, click **Invite People** and add your FinOps stakeholders: eng leadership, finance, the executive sponsor, and the engineers who'll act on recommendations. Assign each person an [organization-level role](/rbac) and, if you set up RBAC above, the right team. See [Invite Users to Your Account](/vantage_account#invite-users-to-your-account) for the step-by-step flow.

    <Tip>
      **For larger orgs, automate team membership.**

      * [SSO group mapping](/sso#set-up-sso-group-mapping-for-teams) places users on the right team based on their identity-provider group.
      * The [Vantage API](https://docs.vantage.sh/api/teams/add-team-member) and the [Terraform provider](https://registry.terraform.io/providers/vantage-sh/vantage/latest/docs/resources/team) cover bulk team membership for existing users.
      * [Using Terraform to Automate Okta SSO Group Access](https://www.vantage.sh/blog/okta-terraform) walks through an end-to-end setup mapping Okta groups to Vantage teams, folders, and access grants.
    </Tip>
  </Step>

  <Step title="Build Your First Cost Report">
    In [Cost Reports](/cost_reports), start broad: **Last 30 Days**, group by **Service**, all providers. Save it as **All Spend**. This is your baseline for every conversation that follows.

    **Or with AI:**

    <Prompt description={`Create a Cost Report titled "All Spend" grouped by service across all providers for the last 30 days.`} actions={["copy"]}>
      Create a Cost Report titled "All Spend" grouped by service across all providers for the last 30 days.
    </Prompt>
  </Step>

  <Step title="Run an &#x22;Untagged Spend&#x22; Report">
    Duplicate the **All Spend** report and filter to rows missing your single most important tag (most teams pick `team` or `cost-center`). Save it as **Untagged Spend**. The goal: drive that number toward zero over the next 30 days.

    This pattern comes directly from how Vantage customers structure their first governance dashboard. See [Cloud Cost Governance](https://www.vantage.sh/blog/cloud-cost-governance).

    **Or with AI:**

    <Prompt description="Show me last month's spend that has no `team` tag, grouped by service." actions={["copy"]}>
      Show me last month's spend that has no `team` tag, grouped by service.
    </Prompt>
  </Step>

  <Step title="Share What You've Seen">
    Send the **All Spend** and **Untagged Spend** reports to your FinOps stakeholders (eng leadership, finance, executive sponsor) with a one-paragraph note: *"this is what we spend, this is what we can't yet attribute, and here's the plan to fix it."*

    This is the start of the [shortened money-feedback loop](https://www.vantage.sh/blog/shortening-money-feedback-loop) and a direct application of the [FinOps Principle](https://www.finops.org/framework/principles/) that *everyone takes ownership for their technology usage*.
  </Step>
</Steps>

### Wrapping Up Week 1

Use the following prompts along with the **Definition of done** below to verify the week's work.

<Accordion title="FinOps Agent Prompts for Week 1" icon="wand-magic-sparkles">
  <Prompt description="Which cost providers and integrations are connected, and what's the status of each?" actions={["copy"]}>
    Which cost providers and integrations are connected, and what's the status of each?
  </Prompt>

  <Prompt description="List my workspaces, the integrations assigned to each, and the people who have access." actions={["copy"]}>
    List my workspaces, the integrations assigned to each, and the people who have access.
  </Prompt>

  <Prompt description={`List my saved Cost Reports and confirm "All Spend" and "Untagged Spend" exist.`} actions={["copy"]}>
    List my saved Cost Reports and confirm "All Spend" and "Untagged Spend" exist.
  </Prompt>
</Accordion>

<Check>
  **Definition of done:** all primary providers **Stable**, one workspace strategy chosen, RBAC configured (if applicable), stakeholders invited, two saved reports (**All Spend** and **Untagged Spend**), one summary note sent.
</Check>

## Week 2: Allocate and Report

<div
  style={{
borderRadius: "12px",
padding: "1.5px",
background: "linear-gradient(135deg, #6742D6 0%, rgba(103, 66, 214, 0.3) 50%, #6742D6 100%)",
marginBottom: "1.5rem"
}}
>
  <div
    style={{
borderRadius: "10.5px",
padding: "1.1rem 1.4rem",
backgroundColor: "light-dark(#FDFCFD, #0F1218)"
}}
  >
    <div
      style={{
  display: "inline-block",
  borderRadius: "8px",
  border: "1px solid light-dark(#E6E2EF, #303341)",
  padding: "0.25rem 0.6rem",
  fontSize: "0.875rem",
  fontWeight: 600,
  backgroundColor: "light-dark(#F7F4FF, #171420)",
  color: "light-dark(#4D2EB2, #B8A8FF)",
  marginBottom: "0.75rem"
}}
    >
      Days 8–14
    </div>

    <p style={{ margin: "0 0 0.5rem 0" }}>
      <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/capabilities/allocation/">Allocation</a> and <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/capabilities/unit-economics/">Unit Economics</a> capabilities · primarily support the <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/phases/#inform">Inform phase</a>
    </p>

    <p style={{ fontStyle: "italic", margin: 0 }}>
      At least 70% of cost is attributed to a known owner. The <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/maturity-model/#crawl">FinOps Foundation Crawl-stage sample KPI</a> is "able to allocate at least 70% of cost to known owner."
    </p>
  </div>
</div>

<Steps>
  <Step title="Decide Your Allocation Hierarchy Before Tagging">
    Pick at most three to five keys, typically `team`, `environment`, `application`, `cost-center`, and `business-unit`. Document them in a shared place your engineers will actually read. The recommended flat core set and the rationale for keeping it small are in [Scaling virtual tags](/guides/scaling_tagging).
  </Step>

  <Step title="Audit Existing Provider Tag Coverage">
    In **Settings > Tags**, look at which keys your providers already emit. If `team` already exists everywhere with consistent values, use it directly. Don't invent a virtual tag rule when the underlying tag is already correct.

    **Or with AI:**

    <Prompt description="What tag keys are available across my providers, and what are the most common values for the `team` tag?" actions={["copy"]}>
      What tag keys are available across my providers, and what are the most common values for the `team` tag?
    </Prompt>
  </Step>

  <Step title="Create Your First Virtual Tag">
    Pick **Custom Value** or **Tag Key Collapsing** to start ([virtual tags](/tagging), [virtual tag examples](/tagging_examples)). Apply the [Scaling virtual tags](/guides/scaling_tagging) guidance from day one:

    * Scope the tag to specific providers, not All Providers.
    * Set the smallest backfill window you actually report on.
    * Prefer equality operators (`is`, `is one of`) over `flexible match`.

    **Or with AI:**

    <Prompt description="Create a virtual tag called `team` that combines the AWS `team` tag and the Kubernetes `organization/team` label." actions={["copy"]}>
      Create a virtual tag called `team` that combines the AWS `team` tag and the Kubernetes `organization/team` label.
    </Prompt>
  </Step>

  <Step title="Save Filtered Views per Team">
    Wrap each team's filter (provider, accounts, the `team` virtual tag you just created) into a [saved filter](/saved_filters). Reports and dashboards scoped to that team can reference it, so changes to membership propagate automatically without touching every report.
  </Step>

  <Step title="Build a Per-Team Showback Dashboard">
    Group your reports into [folders](/folders) and create a [dashboard](/dashboards) per team. This sets up **showback**, or visibility for each team, which the FinOps Foundation [Invoicing & Chargeback capability](https://www.finops.org/framework/capabilities/invoicing-chargeback/) calls "always required in any FinOps practice." Formal chargeback to accounting cost centers is a separate question, dependent on your org's accounting model.
  </Step>

  <Step title="Add Unit-Cost Context">
    Import a [business metric](/business_metrics) and attach it to the **All Spend** report. Start simple (cost per GB stored, cost per token); customer-level metrics come later. This is the FinOps Foundation [Unit Economics capability](https://www.finops.org/framework/capabilities/unit-economics/), and a trend on a stable denominator beats raw monthly spend.
  </Step>

  <Step title="Track Allocation %">
    Review the **Untagged Spend** report from Week 1 and note the percentage drop. The [FinOps Maturity Model](https://www.finops.org/framework/maturity-model/) sample KPIs are "able to allocate at least 70% of cost to known owner" at Crawl, "at least 85%" at Walk, and "greater than 90%" at Run. Use your primary tag, account structure, or another documented allocation rule to measure known-owner allocation. Don't chase Run yet. Crawl is the right target for now.
  </Step>
</Steps>

### Wrapping Up Week 2

Use the following prompts along with the **Definition of done** below to verify the week's work.

<Accordion title="FinOps Agent Prompts for Week 2" icon="wand-magic-sparkles">
  <Prompt description="Show last month's cost grouped by `tag:team` and call out which services still have the most untagged spend." actions={["copy"]}>
    Show last month's cost grouped by `tag:team` and call out which services still have the most untagged spend.
  </Prompt>

  <Prompt description="List my dashboards and the reports inside each." actions={["copy"]}>
    List my dashboards and the reports inside each.
  </Prompt>

  <Prompt description="List my business metrics and which Cost Reports they're attached to." actions={["copy"]}>
    List my business metrics and which Cost Reports they're attached to.
  </Prompt>
</Accordion>

<Check>
  **Definition of done:** at least 70% of cost allocated to a known owner, one dashboard per team, one unit cost in place.
</Check>

## Week 3: Budget, Alert, and Govern

<div
  style={{
borderRadius: "12px",
padding: "1.5px",
background: "linear-gradient(135deg, #6742D6 0%, rgba(103, 66, 214, 0.3) 50%, #6742D6 100%)",
marginBottom: "1.5rem"
}}
>
  <div
    style={{
borderRadius: "10.5px",
padding: "1.1rem 1.4rem",
backgroundColor: "light-dark(#FDFCFD, #0F1218)"
}}
  >
    <div
      style={{
  display: "inline-block",
  borderRadius: "8px",
  border: "1px solid light-dark(#E6E2EF, #303341)",
  padding: "0.25rem 0.6rem",
  fontSize: "0.875rem",
  fontWeight: 600,
  backgroundColor: "light-dark(#F7F4FF, #171420)",
  color: "light-dark(#4D2EB2, #B8A8FF)",
  marginBottom: "0.75rem"
}}
    >
      Days 15–21
    </div>

    <p style={{ margin: "0 0 0.5rem 0" }}>
      <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/capabilities/budgeting/">Budgeting</a>, <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/capabilities/forecasting/">Forecasting</a>, and <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/capabilities/anomaly-management/">Anomaly Management</a> capabilities · supports the <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/phases/#inform">Inform</a> and <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/phases/#operate">Operate</a> phases
    </p>

    <p style={{ fontStyle: "italic", margin: 0 }}>
      Nothing surprises you, and every alert has an owner.
    </p>
  </div>
</div>

<Steps>
  <Step title="Connect Slack or Teams (Not Both)">
    Connect [Slack](/slack) or [Microsoft Teams](/microsoft_teams) for notifications.

    <Warning>
      Cost alerts, anomaly alerts, budget alerts, and report notifications can be delivered to **Slack or Teams, not both**. Pick one.
    </Warning>
  </Step>

  <Step title="Add Budgets to Your Top Reports">
    In [budgets](/budgets), use a standard budget for a flat target and a hierarchical budget (up to 10 levels) when you want a parent budget broken out by team. Period format is `YYYY-MM`.

    **Or with AI:**

    <Prompt description="Create a monthly Budget of $50,000 for my AWS production Cost Report for the rest of the calendar year." actions={["copy"]}>
      Create a monthly Budget of \$50,000 for my AWS production Cost Report for the rest of the calendar year.
    </Prompt>
  </Step>

  <Step title="Configure Cost Alerts and Cost Anomaly Alerts">
    Use [cost alerts](/cost_alerts) for threshold and percent-change rules and [cost anomaly alerts](/cost_anomaly_alerts) for ML-detected spikes. Send everything to one Slack or Teams channel for a week before you fan out by team. It's much easier to tune signal-to-noise that way.

    **Or with AI:**

    <Prompt description="Create a Cost Alert that notifies my #finops Slack channel if any provider's spend exceeds 20% of last month's." actions={["copy"]}>
      Create a Cost Alert that notifies my #finops Slack channel if any provider's spend exceeds 20% of last month's.
    </Prompt>

    <Tip>
      From any anomaly, the FinOps Agent's [**Investigate Anomaly** action](/vantage_finops_agent#investigate-cost-anomalies) produces a root-cause summary in Slack. Ask a teammate to try it the first time one fires.
    </Tip>
  </Step>

  <Step title="Schedule Report Notifications">
    Use [report notifications](/report_notifications) for scheduled digests: daily for the engineering cost channel, weekly digest for finance, monthly summary for execs.
  </Step>

  <Step title="Open Issues for Your Top Three Opportunities">
    Use [issues](/issues) to track optimization work, and link each issue to the Cost Report that proves the savings. This makes optimization a tracked task with an owner, not an item on a list nobody re-reads.

    <Tip>
      Already in Jira? The [Jira integration](/jira) can create Jira issues from cost anomaly alerts, budget alerts, cost alerts, and resource reports, including resource reports for cost recommendations. Issue status syncs back into Vantage daily.
    </Tip>
  </Step>

  <Step title="Establish a Weekly Cadence">
    A 30-minute Friday review covering: anomaly alerts, budget burn, the top three issues, and the untagged % trend.
  </Step>

  <Step title="Spot-Check Forecasting">
    Open any saved Cost Report and confirm the [baseline forecast](/forecasting#baseline-forecast) is plausible one, three, and six months out. If you've changed filters this week, re-save the report so the forecast regenerates.

    <Note>
      [Dynamic forecast](/forecasting#dynamic-forecast), forecasting tied to imported business metrics, is an Enterprise-tier feature.
    </Note>
  </Step>
</Steps>

### Wrapping Up Week 3

Use the following prompts along with the **Definition of done** below to verify the week's work.

<Accordion title="FinOps Agent Prompts for Week 3" icon="wand-magic-sparkles">
  <Prompt description="List my budgets and cost alerts, and tell me which have fired in the last 7 days." actions={["copy"]}>
    List my budgets and cost alerts, and tell me which have fired in the last 7 days.
  </Prompt>

  <Prompt description="List my report notifications and what schedule they're on." actions={["copy"]}>
    List my report notifications and what schedule they're on.
  </Prompt>
</Accordion>

<Check>
  **Definition of done:** budgets on the top reports, anomaly alerts wired to one channel, three issues open with owners, weekly review on the calendar.
</Check>

## Week 4: Optimize and Operate with AI

<div
  style={{
borderRadius: "12px",
padding: "1.5px",
background: "linear-gradient(135deg, #6742D6 0%, rgba(103, 66, 214, 0.3) 50%, #6742D6 100%)",
marginBottom: "1.5rem"
}}
>
  <div
    style={{
borderRadius: "10.5px",
padding: "1.1rem 1.4rem",
backgroundColor: "light-dark(#FDFCFD, #0F1218)"
}}
  >
    <div
      style={{
  display: "inline-block",
  borderRadius: "8px",
  border: "1px solid light-dark(#E6E2EF, #303341)",
  padding: "0.25rem 0.6rem",
  fontSize: "0.875rem",
  fontWeight: 600,
  backgroundColor: "light-dark(#F7F4FF, #171420)",
  color: "light-dark(#4D2EB2, #B8A8FF)",
  marginBottom: "0.75rem"
}}
    >
      Days 22–30
    </div>

    <p style={{ margin: "0 0 0.5rem 0" }}>
      <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/capabilities/usage-optimization/">Usage Optimization</a>, <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/capabilities/rate-optimization/">Rate Optimization</a>, and <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/capabilities/finops-education-enablement/">Education & Enablement</a> capabilities · supports the <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/phases/#optimize">Optimize</a> and <a target="_blank" rel="noopener noreferrer" href="https://www.finops.org/framework/phases/#operate">Operate</a> phases
    </p>

    <p style={{ fontStyle: "italic", margin: 0 }}>
      Book actual savings, put AI in the loop, and turn FinOps from a project into a practice.
    </p>
  </div>
</div>

This week leans on the [FinOps Agent](/vantage_finops_agent) and [Vantage MCP](/vantage_mcp) to shorten the path from analysis to action. The [FinOps Foundation has highlighted agentic AI use cases](https://www.finops.org/insights/ai-for-finops-agentic-use-cases/) for FinOps teams moving from insight to execution.

<Steps>
  <Step title="Work the Recommendations Queue">
    Open [cost recommendations](/cost_recommendations) and filter to your highest-impact provider first. Save the result as a [saved view](/cost_recommendations#saved-views), then [add it to a dashboard](/cost_recommendations#add-saved-recommendation-views-to-dashboards) so progress on those recommendations stays visible alongside spend trends. This is the FinOps Foundation [Usage Optimization capability](https://www.finops.org/framework/capabilities/usage-optimization/) in practice; for the over-provisioning patterns to look for across EC2, EBS, RDS, and container services, see [Rightsizing](https://handbook.vantage.sh/aws/concepts/rightsizing/) in the Cloud Cost Handbook.

    **Or with AI:**

    <Prompt description="List my open AWS cost recommendations ranked by estimated monthly savings. Which three should I prioritize this week?" actions={["copy"]}>
      List my open AWS cost recommendations ranked by estimated monthly savings. Which three should I prioritize this week?
    </Prompt>
  </Step>

  <Step title="Audit Active Resources">
    Use [cost recommendations](/cost_recommendations#recommendation-categories) to find idle and orphaned AWS resources such as unattached EBS volumes, unattached EIPs, idle EC2 instances, and idle RDS instances. Then open the related [active resources](/active_resources) or resource reports to inspect the affected resources before taking action. The cheap, no-architecture-change wins often live here.

    **Or with AI:**

    <Prompt description="List my AWS EC2 instances costing more than $100 per month and flag any that look idle." actions={["copy"]}>
      List my AWS EC2 instances costing more than \$100 per month and flag any that look idle.
    </Prompt>

    <Tip>
      If your organization has connected the [Datadog MCP connector](/datadog_agent), ask the FinOps Agent to confirm utilization with live telemetry before you act, for example *"Which of these EC2 instances show low CPU and memory in Datadog over the last two weeks?"* This verifies a resource is truly idle rather than acting on cost alone.
    </Tip>
  </Step>

  <Step title="Kubernetes Efficiency (If Applicable)">
    In [Kubernetes](/kubernetes), open the **Kubernetes efficiency reports** for pod-level rightsizing recommendations. See [How Vantage calculates Kubernetes rightsizing recommendations](/cost_recommendations#how-vantage-calculates-kubernetes-rightsizing-recommendations) for the 80% efficiency target and the formulas behind each recommendation, and [Kubernetes Rightsizing](https://handbook.vantage.sh/kubernetes/kubernetes-rightsizing/) in the Cloud Cost Handbook for the request/limit concepts behind it. If you don't run Kubernetes, swap this step for another sweep through [cost recommendations](/cost_recommendations).
  </Step>

  <Step title="Financial Commitments Review">
    Open [financial commitment reports](/financial_commitment_reports). Financial commitment reports currently support AWS only and require the CUR to be ingested. The [FinOps Maturity Model](https://www.finops.org/framework/maturity-model/) sample KPIs for commitment discount target coverage are "approximately 60%" at Crawl, "greater than 75%" at Walk, and "greater than 80%" at Run. If your commitment coverage is well below 60%, queue a commitments conversation with finance.
  </Step>

  <Step title="Roll Out the FinOps Agent and Vantage MCP If You Haven't Already">
    The [FinOps Agent](/vantage_finops_agent) and [Vantage MCP](/vantage_mcp) use the same underlying read and write tools, exposed to different audiences. Some teams will have set up one or both earlier; this week, make sure each surface is in front of the people who'd use it.

    * **FinOps Agent in Slack** for FinOps practitioners and managers. Pick the channel where your weekly review happens. An Org Owner has to approve any AWS remediation actions ([RBAC permissions](/rbac_permissions)). Run a few opening prompts together with a teammate:
      * *"Summarize this week's spend for me."*
      * *"Open an issue for the largest active recommendation."*
      * *"Investigate the most recent anomaly."*
    * **Vantage MCP in the editor** for engineers already in Cursor, Claude Code, or Goose. They can query Vantage from their IDE without context-switching to the console. Try: *"What's the unit cost of the checkout service this month?"*
    * **[Canvas](/canvas) in the console** for anyone who wants the agent's answer as a saved, refreshable table instead of a one-off chat reply. Turn the recurring prompts from earlier weeks into durable reports you can re-run. Try: *"Show cost per team by service for the last three months as a table."*

    See the [FinOps AI Prompt Guide](/guides/finops_ai_prompt_guide) for more prompt patterns.
  </Step>

  <Step title="Codify What's Stable with Terraform (If Applicable)">
    <Note>
      If your team doesn't use Terraform, skip this step. The [Vantage API](/api) covers the same resources programmatically if you'd rather script changes another way.
    </Note>

    Pick the three to five reports, budgets, or virtual tags you re-edit by hand the most and move them to the [Vantage Terraform provider](/terraform), following [FinOps as Code](/guides/finops_as_code).

    Use AI to draft the Terraform, then commit the reviewed configuration through your normal Terraform workflow.

    **Or with AI:**

    <Prompt description="Write me a Terraform script for the virtual tag I just created in the Vantage console." actions={["copy"]}>
      Write me a Terraform script for the virtual tag I just created in the Vantage console.
    </Prompt>

    <Warning>
      When using a [service token](/api/authentication#create-a-vantage-api-service-token) with Terraform, assign it to the **Everyone** team. Service tokens on the Everyone team have the permissions needed for organization-level actions like managing provider integrations, creating teams, and managing [virtual tags](/tagging). Tokens on other teams will hit authorization errors for those operations.
    </Warning>
  </Step>

  <Step title="Pick Role-Based Learning Paths">
    Send each persona the matching [Vantage University](/vantage_university) track:

    <CardGroup cols={3}>
      <Card title="FinOps Analyst" icon="chart-line" href="/vantage_university_finops_analyst">
        For practitioners owning cost visibility and allocation.
      </Card>

      <Card title="Developer" icon="laptop-code" href="/vantage_university_developer">
        For engineers acting on recommendations.
      </Card>

      <Card title="Finance Manager" icon="coins" href="/vantage_university_finance_manager">
        For finance partners on budgets and forecasting.
      </Card>
    </CardGroup>

    As a practical Vantage rollout cadence, start with one module per role per week. This supports the FinOps Foundation [Education & Enablement capability](https://www.finops.org/framework/capabilities/finops-education-enablement/).
  </Step>

  <Step title="Look Back, Plan Forward">
    Run a 30-minute review with stakeholders covering allocation %, anomaly counts, issues closed and savings booked, and recommendations adopted.

    Then pick one [FinOps capability](https://www.finops.org/framework/capabilities/) to advance from [Crawl to Walk](https://www.finops.org/framework/maturity-model/) over the next 30 days, and put it on the roadmap.
  </Step>
</Steps>

### Wrapping Up Week 4

Use the following prompts along with the **Definition of done** below to verify the week's work.

<Accordion title="FinOps Agent Prompts for Week 4" icon="wand-magic-sparkles">
  <Prompt description="What was my month-over-month change in spend, and what drove it?" actions={["copy"]}>
    What was my month-over-month change in spend, and what drove it?
  </Prompt>

  <Prompt description="What's my current commitment coverage across providers, and where could I improve?" actions={["copy"]}>
    What's my current commitment coverage across providers, and where could I improve?
  </Prompt>
</Accordion>

<Check>
  **Definition of done:** at least one optimization booked, a saved recommendations view pinned to a dashboard, the FinOps Agent installed in Slack with at least one teammate using it, one engineer querying via MCP, a written "next 30 days" plan grounded in the [FinOps Foundation capabilities](https://www.finops.org/framework/capabilities/).
</Check>

<Card title="You've completed the 30-day playbook" icon="flag-checkered">
  The Crawl-stage foundation is the start, not the finish. Pick one [FinOps capability](https://www.finops.org/framework/capabilities/) to advance from [Crawl to Walk](https://www.finops.org/framework/maturity-model/) and rerun the playbook with a sharper focus.
</Card>

## Frequently Asked Questions

<AccordionGroup>
  <Accordion title="Do I need a paid plan to do this playbook?">
    Most of it works on the free tier. The notable exceptions:

    * **Automated [FinOps Agent](/vantage_finops_agent) remediation** is for paying accounts.
    * **Advanced [RBAC](/rbac)** (locking down the Everyone team, scoped team workspace access) is Enterprise tier.
    * **[Dynamic forecast](/forecasting#dynamic-forecast)** tied to imported business metrics is Enterprise.

    None of those are required to reach the Week 4 outcomes. They're listed where they apply so you can plan around them.
  </Accordion>

  <Accordion title="Can I move faster than 30 days?">
    Yes. The pace is suggested, not strict. Many customers finish Week 1 in a couple of days. The 30-day frame is for the **rhythm** (weekly review, anomaly response, monthly capability advancement), not the setup. The [FinOps Foundation Phases](https://www.finops.org/framework/phases/) page is explicit that practitioners cycle quickly through Inform/Optimize/Operate as they mature.
  </Accordion>

  <Accordion title="We're already past Week 1. Where do we jump in?">
    Run the **Definition of done** check at the end of each week. Start at the first week whose checks aren't all green. Most teams who've used Vantage informally for a while are missing pieces of Week 2 (allocation hierarchy, unit cost) or Week 3 (budgets and a real weekly cadence). Both are worth doing properly even if it feels like backtracking.
  </Accordion>
</AccordionGroup>