{ "schema": "aiblocks-page/1", "id": "agency-automation-governance-architect", "type": "agent", "name": "Automation governance planner", "summary": "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.", "headline": "Automation governance planner", "subhead": "Describe a process you want to automate and the tools it touches. It scores time saved, data risk, outside dependencies and growth, then gives one verdict from approve to reject, a safe design, owners and the tests to pass before you switch it on.", "job": { "id": "set-up-ai", "name": "Set up AI to work for you" }, "level": "intermediate", "thinking": "high", "tested": true, "updated": "2026-11-03", "first_published": "2026-10-26", "inputs": [ { "type": "question", "required": true, "label": "Question", "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like" }, { "type": "document", "required": false, "label": "Document", "what": "a finished document, such as a Word file, a PDF or a page of notes" } ], "outputs": [ { "type": "audit_report", "required": true, "label": "Audit report", "what": "findings with evidence, severity, missing inputs and next actions" }, { "type": "plan", "required": true, "label": "Plan", "what": "a dated plan: what to do, in what order, with a decision rule for each step" } ], "you_give": [ "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)" ], "you_get": [ "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" ], "use_when": [ "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." ], "skip_when": [ "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." ], "output_sample": { "input": [ "The process in plain steps, and what you want automated", "The tools and systems it touches", "How often it runs, how long it takes by hand and what data it handles", "Who owns it (optional)" ], "prerequisites": [ "A workflow export from n8n, Zapier or Make, if the automation already exists (optional)" ], "output": [ { "name": "Process summary", "contains": "The process, its goal, the current flow and the systems involved." }, { "name": "Audit evaluation", "contains": "Scores for time saved, data risk, outside dependencies and growth." }, { "name": "Verdict", "contains": "One of approve, approve as pilot, partial automation only, defer or reject." }, { "name": "Rationale", "contains": "The business impact, the key risks and why this verdict was chosen." }, { "name": "Recommended design", "contains": "Ten stages with an error path and a manual fallback." }, { "name": "Implementation standard", "contains": "Naming and version rules, documents, tests and monitoring." }, { "name": "Systems and owners", "contains": "For each connected system, its role, its owner and what it may change." }, { "name": "Preconditions and risks", "contains": "Approvals, limits and rollout guardrails needed before go-live." } ] }, "output_shape": "PROCESS SUMMARY\n Name | Goal | Current flow | Systems | MISSING \n\nAUDIT EVALUATION\n Time saved | Data risk | Dependency risk | Growth \n\nVERDICT\n \n\nRATIONALE\n Business impact | Key risks | Why this verdict \n\nRECOMMENDED DESIGN\n Trigger | Input checks | Clean-up | Business rules | Actions | Result check | Log | Error path | Manual fallback | Status update\n\nIMPLEMENTATION STANDARD\n Name | Documents needed | Tests | Monitoring \n\nSYSTEMS AND OWNERS\n | | | | \n\nPRECONDITIONS AND RISKS\n Approvals | Limits | Rollout guardrails ", "how_to_use": [ "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." ], "checks": [ "The result addresses your actual task and cites the evidence used.", "Examples, role-play experience and targets are kept separate from verified results.", "Claims of tests, memory, tool access or completed actions match what actually happened." ], "next": [ { "name": "Zapier and Make automation planner", "url": "https://useaiblocks.com/skills/no-code-automation-planner", "why": "Zapier and Make automation planner" } ], "source": { "by": "Michael Sitarzewski and Agency Agents contributors", "repo": "msitarzewski/agency-agents", "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/specialized/automation-governance-architect.md", "licence": "MIT", "original_name": "Automation Governance Architect", "commit": "b37b5bb33b78f2c1d6567d98e25ca818e3259219" }, "credits": [ { "title": "Automation Governance Architect", "by": "Michael Sitarzewski and Agency Agents contributors", "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/specialized/automation-governance-architect.md", "used": "Original agent profile, preserved in references/source-agent.md; AI Blocks adds setup and review instructions." } ], "files": [ "LICENSE", "references/source-agent.md", "SETUP.md", "source.json" ], "links": { "page": "https://useaiblocks.com/agents/agency-automation-governance-architect", "markdown": "https://useaiblocks.com/agents/agency-automation-governance-architect.md", "json": "https://useaiblocks.com/agents/agency-automation-governance-architect.json", "instructions": "https://useaiblocks.com/skills/agency-automation-governance-architect/SKILL.md", "download": "https://useaiblocks.com/skills/agency-automation-governance-architect.zip", "api_item": "https://useaiblocks.com/api/v1/items/agency-automation-governance-architect", "api_document": "https://useaiblocks.com/api/v1/documents/agent/agency-automation-governance-architect", "mcp": "https://useaiblocks.com/mcp" } }