Hire an AI automation governance planner

Everything it can hand back

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

• One verdict: approve, approve as a pilot, automate part only, defer or reject, with the reason
• Scores for time saved, data risk, outside dependencies and growth
• A safe design with ten stages, an error path and a manual fallback
• Naming and version rules, and what to log on every run
• A list of tests to pass before go-live
• For each connected system, its role, its owner and what it may change

How it does the job well

• Do not approve an automation only because it can be built.
• Do not recommend direct changes to a live critical workflow without the user's explicit approval.
• Prefer simple and sturdy over clever and fragile.
• Every recommendation names a fallback and an owner.
• If hours saved or frequency are missing, say the value is unclear. Lean to DEFER or APPROVE AS PILOT. Do not invent hours or savings.
• Clarify the purpose, audience and limits, such as length, format and deadline, first.
• Use the user's materials and voice. Ask for samples when tone matters.

Mistakes it avoids

• Approving because the tool can do it.
• Fixing a failing live workflow in place.
• Unowned systems and unnamed fallbacks.
• Vague workflow names such as "final", "new test" or "fix2".
• Generic output that ignores the user's details.
• Inventing facts, quotes or sources.

What a good result looks like

An example, not your task: Someone asks "can we automate this?" and you need a clear yes, no or pilot.

• Process summary. The process, its goal, the current flow and the systems involved.
• Audit evaluation. Scores for time saved, data risk, outside dependencies and growth.
• Verdict. One of approve, approve as pilot, partial automation only, defer or reject.
• Rationale. The business impact, the key risks and why this verdict was chosen.
• Recommended design. Ten stages with an error path and a manual fallback.
• Implementation standard. Naming and version rules, documents, tests and monitoring.

How the work is checked

• The output meets the stated length and format.
• Every fact comes from the user's material or is marked to check.
• Suggested changes explain why.
• 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.

A second opinion

Before it hands back, your AI reviews the draft the way Ada Lovelace and Grace Hopper would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Pin the process. It restates the process, the goal, the current flow and the systems. It asks once for anything missing, then marks it MISSING.
• Score four checks. It rates time saved, data risk, outside dependency risk and how the process holds up as volume grows.
• Give one verdict. It picks exactly one of approve, approve as pilot, partial automation only, defer or reject.
• Explain the verdict. It gives the business impact, the key risks and why this verdict and not the next one.
• Design the safe version. It sets the ten stages, the error branch and the manual fallback, with duplicate protection and safe retries.
• Set the standards. It adds naming and version rules, the logging list, the test list and who owns each system.
• List preconditions. It names the approvals, limits and rollout guardrails needed before anything goes live.

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 automation-governance-architect 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/automation-governance-architect/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

• The process in plain steps: what happens now and what you want automated.
• The tools and systems it touches, such as a CRM, email, billing or a spreadsheet.
• How often it runs and how long it takes by hand each time.
• What data it handles, such as customer, payment or contract records.
• Who owns the process and who fixes it when it breaks (optional)
• The tool you plan to use, such as n8n, Zapier or Make (optional)

Helpful context (optional)

• An export of the existing workflow from n8n, Zapier or Make.
• A log of recent failures or manual fixes, so the risks come from what really happened.
• The names of the owner of each connected system.

Tools and access

• Claude, ChatGPT or Gemini with file upload: You can upload a workflow export or a process document, so the review uses your real steps.

Functions and deliverables

• Automation governance planner: Decide if a business process should be automated. Get a verdict, the risks, a safe design with fallback and the tests to pass before go-live.
  • One verdict: approve, approve as a pilot, automate part only, defer or reject, with the reason
  • Scores for time saved, data risk, outside dependencies and growth
  • A safe design with ten stages, an error path and a manual fallback
  • Naming and version rules, and what to log on every run
  • A list of tests to pass before go-live
  • For each connected system, its role, its owner and what it may change
  Source: Michael Sitarzewski and Agency Agents contributors.
• Routine task automation planner: Plan which repeat chores to automate. List your weekly tasks and get ranked picks, steps a new hire can run, and a small first version.
  • A list of chores worth handing to a tool, ranked
  • The parts of each chore, split into what stores, what works and what gives orders
  • Written steps a new hire can run, with terms defined
  • A small first version and a check against the hand method
• HR process automation designer: Name your HR processes, like onboarding. Get which to automate, which tool fits each and a build order.
  • A ranked list of tasks to automate
  • Workflow designs for key processes
  • Tool suggestions for each flow
  • A business case and build order
  Source: Tuan Duc Tran.
• Zapier and Make automation planner: Describe the trigger, apps and result. Compare Zapier and Make patterns, map the steps and plan tests, costs and failure handling.
  • A tool recommendation with reasons
  • A trigger, filter and action layout
  • Test and naming tips
  • A sign for when to switch to code
  Source: sickn33.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up
• Ada Lovelace: Explain a tool, check its claims and explore new uses through Ada Lovelace’s recorded approach. Use clear steps and worked examples.
  • Your problem worked on the way Ada Lovelace would: their questions, their method, their push-back
  • The answer or the work, in Ada Lovelace's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Grace Hopper: Make a tool or task easier to use through Grace Hopper’s recorded approach. Use people’s words, automate dull work and document clear steps.
  • Your problem worked on the way Grace Hopper would: their questions, their method, their push-back
  • The answer or the work, in Grace Hopper's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Someone asks "can we automate this?" and you need a clear yes, no or pilot.
• An automation already exists and keeps failing, duplicating records or needing manual fixes.
• You plan to connect a CRM, a billing tool or a booking system and want rules for who owns what.
• You need a handover document so another person can run an automation.

Limits to check before starting

• You have decided to automate and only want a Zapier or Make setup. Use the Zapier and Make automation planner.
• You want an n8n workflow laid out. Use the n8n workflow designer, then bring the design here for review.
• Your automation is already built and you want its failures checked. Use the workflow Automation reliability reviewer.
• You want a full spec for a software workflow with every failure path. Use the Workflow specification writer.
• You need a legal or privacy ruling on the data it handles. Ask a qualified professional.

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 from this page 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.
• Describe the process in plain steps. Include the systems, how often it runs, how long it takes by hand and what data it handles. Paste a workflow export if the automation already exists.
• Type "Evaluate this process for automation. Score the four checks, give one verdict and list the preconditions. Do not guess any system or owner I did not name."
• Read the verdict and the risks first. If you disagree, say why and ask it to score again.
• If the verdict is approve or pilot, give the design and the test list to whoever builds it. Do not switch on a live workflow until every test passes.
• Ask for a new review when volume jumps, a tool changes or the same manual fix keeps coming back.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/automation-governance-architect 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.