Hire an AI AWS cost and resilience reviewer

Everything it can hand back

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

• Resource cost findings
• Architecture risks
• Prioritized change and rollback plan

How it does the job well

• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.
• Treat input from users, files and networks as untrusted. Validate it at the boundary.

Mistakes it avoids

• 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: You want to cut your AWS bill and need to know which savings would weaken reliability or security.

• Resource cost findings. Each saving tied to a named resource, with current cost, proposed change, risk, effort and a priority score.
• Architecture risks. Findings across the six AWS Well-Architected pillars, each rated high, medium or low risk, with a fix.
• Rollout and rollback plan. Preflight checks, rollout stages, health signals, rollback steps and who to tell.
• Prioritized change list. Savings and risk fixes in one order, so you see which saving costs you resilience.
• Hand-back summary. Source coverage, missing facts and one next action.

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

• AWS resource cost reviewer. Share your AWS setup. Get cost findings and proposed fixes tied to the resources your app uses.
• AWS workload practice reviewer. Share your AWS design. Get architecture gaps and proposed fixes against AWS workload guidance.
• Service rollout and rollback planner. Share a release or infrastructure change. Get preflight checks, rollout stages, health signals and a rollback plan.

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 review-aws-cost-and-resilience 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/review-aws-cost-and-resilience/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

• A bill export or cost report, with its date window
• Your infrastructure files (Terraform, CloudFormation or CDK) and a list of the AWS resources in use
• Your design files or diagrams, and any uptime or compliance targets
• The change you plan to make, and when

Functions and deliverables

• AWS cost and resilience reviewer: Share AWS resource details, bills and architecture. Get savings options, workload risks, change priorities and a rollback plan.
  • Resource cost findings
  • Architecture risks
  • Prioritized change and rollback plan
• AWS resource cost reviewer: Find where your AWS setup wastes money. Get an AWS cost optimization review with fixes, saved as GitHub issues you can track.
  • A cost summary: resources reviewed, current monthly cost and possible monthly savings
  • One GitHub issue per saving, with the saving, risk, effort, usage evidence and steps to check
  • One tracking issue with a diagram of your resources, a ranked checklist and success goals
  Source: GitHub Copilot community.
• AWS architecture reviewer: Review your AWS setup for gaps in security, reliability and cost. Get an AWS Well-Architected review with fixes, then GitHub issues to track them.
  • A diagram of the AWS services found in your files
  • A check against all six pillars, with each finding rated High, Medium or Low
  • A summary of finding counts and top High risk items, shown before anything is created
  • One GitHub issue per finding, with the fix, a command line fallback and a checklist
  • One tracking issue with a table of findings by pillar and a ranked checklist
  Source: GitHub Copilot community.
• Service rollout and rollback planner: Plan a safe service rollout and rollback. Share your release or infrastructure change and get preflight checks, stages, health signals and a rollback plan.
  • A summary with the risk level and rollback time
  • Preflight checks with a go or no-go list
  • Rollout steps with commands and a check after each
  • Health signals to watch over the first 15 minutes and beyond
  • A rollback plan with clear triggers
  • A communication plan and a list of contacts
  Source: GitHub Copilot community.
• 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

• You want to cut your AWS bill and need to know which savings would weaken reliability or security.
• You plan an infrastructure change and want preflight checks and a rollback plan that account for those risks.
• You have a bill export and design files, but no one has weighed cost against risk.

Limits to check before starting

• Your setup runs on Azure, not AWS: use Azure resource costs and resilience reviewer.
• Something is broken on AWS right now: use AWS incident investigation planner.
• You only want to cut the cost of your build and test runs: use GitHub Actions workflow reviewer.

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.

• Add the complete skill pack to your AI.
• Share your bill export, infrastructure files and the change you plan.
• Do not paste AWS access keys into the chat. Give read-only access only if you want live resources read.
• Ask it to follow the steps and mark any missing facts.
• Review the result before making any change in AWS.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/review-aws-cost-and-resilience 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.