Hire an AI cloud cost analyst

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• Spend by team and service, with the share nobody owns.
• A ranked list of waste to remove, each with a dollar figure from your data and an owner.
• Savings from resizing and scheduling, each with its risk to reliability.
• A list of hidden costs, such as data transfer and old snapshots.
• A commitment plan sized to your steady baseline, plus alerts and a unit cost view if you gave counts.

How it does the job well

• Use only figures in the user's data. Do the maths from it and show the working. If a figure is not in the data, write MISSING. Never quote a price, a typical saving or a discount percentage from memory.
• Order matters: ownership, then waste, then rightsizing, then hidden costs, then commitments. Do not suggest a commitment while large waste remains.
• Never trade reliability for savings. Resizing must keep headroom for the user's stated limits. If the limit is unknown, mark the resize as HOLD until headroom is confirmed.
• Never suggest a commitment for a system the user says may move, change or end during the term. Ask first. Size any commitment to the steady baseline, not to peaks, and leave room for growth.
• A short window can mistake a spike for normal use. Say so if the data is under 30 days.
• Allocation before optimization. You cannot optimize spend you can't attribute. Fix tagging and account structure first — an unallocated bill is a mystery, not a target.
• Never trade a reliability incident for a cost saving. Rightsizing that removes real headroom, or an aggressive commitment that forces bad architecture, costs more than it saves. Availability and performance SLOs are constraints, not variables.

Mistakes it avoids

• Quoting savings percentages from the profile or from memory.
• Treating the total bill as the target. A bill that grows slower than customers is not waste. Use unit cost if counts exist.
• Treating a cost report as proof of what a system does. Ask the owner.
• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: Your AWS, Google Cloud or Azure bill is rising and nobody can say why.

• Scope. The cloud, the period, total spend from your data, your reliability limits and assumptions.
• Ownership. Spend by team and service, and the share that has no owner.
• Waste list. Idle and forgotten resources, each with a cost from your data, a risk and an owner.
• Resize and schedule. Systems to shrink or switch off at night, with the saving and the headroom kept.
• Hidden costs. Data transfer, NAT, storage and snapshot costs, with the cause and a fix to test.
• Commitment plan. Which steady workloads could take a discount commitment, and what to confirm first.

How the work is checked

• The changed files build, and the relevant tests and linters pass. The commands and results are shown.
• Each change is explained in one line with its reason, and risky areas are named.
• Any check that could not run is reported as NOT_RUN with what it needs.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Check who owns the spend. It maps cost to team, service and environment and shows how much has no owner.
• Find the waste. It lists idle and forgotten resources and non-production systems left on, ranked by dollars.
• Check the size of systems. It looks for systems bigger than their usage needs, and keeps the headroom your reliability goals require.
• Trace hidden costs. It looks at data moved between zones and regions, NAT gateway traffic, storage tiers and old snapshots.
• Plan commitments last. It sizes discount commitments to your steady baseline, and holds off on any system that is about to change.
• Set owners and alerts. It sends each saving to the team that controls it, and plans spend alerts and a cost per customer view.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id engineering-finops-engineer only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/engineering-finops-engineer/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your cost report, such as an AWS Cost and Usage Report, a Google Cloud billing export or an Azure Cost Management export, for 30 to 90 days.
• Your accounts or projects, and how they map to teams, if you know.
• Which systems are production and which are test or dev.
• The reliability you must keep, such as "the app must handle a traffic spike" or "no slower than today".
• Moves you plan, such as a migration or a rebuild in the next year (optional)
• Customer or order counts for the same months, for cost per customer (optional)

Helpful context (optional)

• A cost export grouped by service and account, plus a tag report.
• A list of what runs in production and what is test.
• Your team's roadmap for the year, so it does not suggest commitments for systems you will move.

Tools and access

• Claude, ChatGPT or Gemini: A model that can read a CSV makes the maths easier. Check each total against your own report. No web access is needed.

Functions and deliverables

• Cloud cost analyst: Find where your cloud bill goes and what to cut safely. Get spend by owner, ranked savings with their risk, and what to commit to last.
  • Spend by team and service, with the share nobody owns.
  • A ranked list of waste to remove, each with a dollar figure from your data and an owner.
  • Savings from resizing and scheduling, each with its risk to reliability.
  • A list of hidden costs, such as data transfer and old snapshots.
  • A commitment plan sized to your steady baseline, plus alerts and a unit cost view if you gave counts.
  Source: Michael Sitarzewski and Agency Agents contributors.
• Customer cancellation risk finder: Share usage, support, billing and engagement data. Get account risk scores, warning signs and possible next steps.
  • A risk score per account
  • Four risk tiers
  • Key signals for each account
  • A recommended action per tier
  Source: Burhan Sebin.
• Google Cloud architecture planner: Share app needs, traffic, budget and constraints. It proposes services, estimates costs from stated assumptions and drafts deployment steps.
  • A recommended architecture
  • Services chosen with reasons
  • A monthly cost estimate
  • Infrastructure code and deploy steps
  Source: Alireza Rezvani.
• AWS cost waste finder: Find idle servers, loose disks and other AWS waste, with a ranked list of fixes and what each could save you every month.
  • Spend by service, region and tag, with the months that jumped
  • A table of idle and unused resources, sorted by monthly saving
  • A reason and a confidence level for every row
  • Right-sizing and savings plan options
  • A list of what it could not check
  Source: sickn33.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.

Tasks you can use it for

• Your AWS, Google Cloud or Azure bill is rising and nobody can say why.
• Finance asks which team or product each cloud dollar belongs to.
• You are about to buy reserved instances or a savings plan and want to check it is safe to commit.
• You want to see cloud cost per customer or per order, not only the total.

Limits to check before starting

• You want to review your monthly cloud and AI bills as a routine. Use the Cloud and AI bills, waste and spend limits.
• You want to cap what your app spends on AI model calls. Use the AI model routing planner.
• You want real-time cost alerts or budget changes made for you. Use your cloud provider's own cost tools. This agent writes a plan only.
• You want reliability goals and alerts for a service. Use the SRE agent.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack and add it to your AI as a skill. If you cannot, paste SKILL.md into a new chat, then paste references/source-agent.md.
• Export your cost report as a CSV or paste the top lines by service and account. Remove account IDs you do not want to share. Do not paste keys or passwords.
• Type "Review this cloud spend. Ownership first, then waste, then resizing, then commitments last. Use only my numbers. Mark every assumption."
• Check the ownership table first. If a big share has no owner, fix that before you cut anything.
• Review each saving with the team that owns the system. Skip any that removes headroom you need.
• Make changes in the cloud console or code yourself. The AI cannot read your account or change anything.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/engineering-finops-engineer for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.