Hire an AI backup restore rehearsal planner

Everything it can hand back

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

• A list of your systems ranked by how fast you need them back
• Recovery targets for each rank, using your numbers
• A rehearsal checklist with prerequisites, stop points, rollback steps and one row per system
• An evidence log template to record what happened and where the proof is saved
• An action list with an owner and a date for each task and gap

How it does the job well

• Never restore over live production data. Every test targets the approved test environment only.
• Never run a restore, delete a backup, change a setting or send a message yourself. Write the steps for a person to run.
• A backup is recoverable only after a restore has been checked. Until then, write "not yet proven".
• 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 have backups but nobody has restored from them lately.

• Inventory and tiers. Each system with its backup and last restore test, ranked by how fast it must come back.
• Recovery targets. How much data loss and downtime you accept for each rank, using your own numbers.
• Rehearsal checklist. Prerequisites, stop points, rollback steps and a row per system for time, data checked and pass or fail.
• Evidence log template. Blank rows to record the backup date, restore times, who checked and where the proof is saved.
• action-register.csv. One row per task or gap, with owner, due date and the source it came from.
• Hand-back summary. Files saved, facts that could not be checked and the single next step.

How the work is checked

• Every system has a rank, a target and a rehearsal row, or a MISSING: line saying why not.
• No system is called recoverable unless a restore was checked and the proof is cited.
• Every test targets the approved test environment, with no step that touches live data.
• Every date and figure traces to a source you were given or is labelled as an assumption.
• 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

• Backup and recovery planner. Lists each system, ranks it by how fast it must return and sets time and data-loss targets. It hands the ranked list and targets to the next step.
• Incident runbook writer. Writes the safe restore test for each system, with prerequisites, stop points and rollback steps. It hands the checklist to the register.
• Executive action register keeper. Turns tasks, evidence to collect and gaps into one action list with owners and dates. It never assigns work to a person without your say.

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 build-a-backup-recovery-rehearsal 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/build-a-backup-recovery-rehearsal/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 list of your critical files and systems and where their data lives
• Your current backup records, such as the tool, how often it runs and the last successful date
• How much data loss and downtime you can take for each system
• Where a test restore is allowed, such as a spare server or test account
• Who owns each system, and your team size (optional)
• Meeting notes or earlier recovery plans (optional)

Helpful context (optional)

• The last backup report or log from your backup tool, with dates.
• A named reviewer who signs off the test.

Tools and access

• Claude, ChatGPT or Gemini with file support: They can read your backup records as pasted text or files. None of them can run a restore for you.

Functions and deliverables

• Backup restore rehearsal planner: Map what needs to be restored, write a safe rehearsal checklist and track the evidence needed to check recovery.
  • A list of your systems ranked by how fast you need them back
  • Recovery targets for each rank, using your numbers
  • A rehearsal checklist with prerequisites, stop points, rollback steps and one row per system
  • An evidence log template to record what happened and where the proof is saved
  • An action list with an owner and a date for each task and gap
• Backup and recovery planner: Describe systems and agreed loss and downtime limits. Get a backup plan, restore steps and drills, with results when actually run.
  • A list of your systems ranked by how much you need them back
  • Recovery targets for each rank
  • A backup design, or a review of what you have
  • A restore guide for each system
  • A drill plan and a schedule for the next drill
  Source: RampStack.
• Incident runbook writer: Name your service. Get a runbook with severity levels, first steps, fixes and who to tell.
  • A severity table
  • Step-by-step response stages
  • Commands and checks to run
  • Escalation paths
  • Message templates
  Source: sickn33.
• Action item tracker: Share meeting notes or email threads. Get action items with owners, deadlines and unresolved commitments.
  • action-register.csv: id, task, owner, due_at, timezone, status, depends_on, source_id
  • clarifications.md
  • proposed-task-changes.md
• 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 have backups but nobody has restored from them lately.
• An auditor, insurer or customer asks for proof that you can recover.
• You moved hosting, changed backup tools or lost a person who knew how it works.
• You want a written recovery plan before something goes wrong, with a checklist someone else could follow.

Limits to check before starting

• Something is down right now. Follow your provider's incident process or call their support. This prepares ahead.
• You would restore over live production data. Do not run this. It is for an approved test environment only.
• You only want a general recovery plan with no test. Use the Backup and recovery planner.
• You only want a response guide for outages. Use the Incident runbook writer.
• Your device needs a safe update and rollback test. Use the Firmware update recovery test planner workflow.

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 handoff pack. It is a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude, ChatGPT or Gemini and say "Follow HANDOFF.md".
• Paste your system list, backup records and targets. Say where a test restore is allowed.
• Read the ranking and targets first. Fix any number the AI got from you wrong before it writes the checklist.
• Run the rehearsal yourself, fill in the evidence log and bring the result back to close the gaps.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/build-a-backup-recovery-rehearsal 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.