{
 "schema": "aiblocks-page/1",
 "id": "agency-operations-manager",
 "type": "agent",
 "name": "Operations manager agent",
 "summary": "Find where your process wastes time and why. Get a ranked list of bottlenecks with evidence, root causes, measures to track and fixes.",
 "headline": "Operations manager agent",
 "subhead": "Describe a process that is slow, late or error-prone, and give any numbers you have. Your AI maps the steps, finds the waiting and rework, and traces each problem to its cause. You get a ranked bottleneck list with fixes, measures to track and a short plan.",
 "job": {
  "id": "document-work",
  "name": "Write down how work gets done"
 },
 "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": "spreadsheet",
   "required": false,
   "label": "Spreadsheet",
   "what": "a spreadsheet with its data, formulas and charts"
  }
 ],
 "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 or problem, in plain words, with who does each step and what tools they use",
  "Any numbers you have, such as volume per week, time per step, error counts and late jobs",
  "The goal, such as faster turnaround, fewer errors or lower cost",
  "Team size and working hours (optional)",
  "Vendor contracts or service levels that touch the process (optional)"
 ],
 "you_get": [
  "A one-page map of the current process, with inputs, steps, outputs and who each one serves",
  "A ranked list of bottlenecks, each with its evidence, likely root cause and who should own it",
  "A baseline table of what you measure today and what is missing",
  "Fix options sorted by effect and effort, with the reason for each rating",
  "A short list of measures to track and a draft procedure for the process (on request)",
  "A list of single points of failure and the backup each one needs"
 ],
 "use_when": [
  "Orders, tickets or invoices are late, and you do not know which step is the cause.",
  "Only one person knows how a key job is done, and you worry about what happens if they leave.",
  "Work is growing, and you need to know if you need more people or a better process.",
  "You must turn how the team works today into a written procedure and a set of measures."
 ],
 "skip_when": [
  "You need a growth or ad bottleneck found in your store numbers. Use the Growth bottleneck finder.",
  "You want a review of a team's testing or delivery workflow. Use the Workflow improvement reviewer.",
  "You want a procedure for a single task or an incident. Use the Incident runbook writer, or ask the Engineering documentation writer for the doc."
 ],
 "output_sample": {
  "input": [
   "A description of the process step by step, with who does each step",
   "Any numbers you have, such as volume, time per step and error counts",
   "Your goal for the process",
   "Vendor service levels that touch it (optional)"
  ],
  "output": [
   {
    "name": "Process map",
    "contains": "Who feeds the process, the steps in order with owners and times, and who receives the result."
   },
   {
    "name": "Baseline",
    "contains": "The figures you have today and the measures that are missing, with how to collect them."
   },
   {
    "name": "Ranked problems",
    "contains": "Each bottleneck with its evidence, root cause, owner role and a rough effort rating."
   },
   {
    "name": "Fix options",
    "contains": "Fixes sorted by effect and effort, each with how to pilot and measure it."
   },
   {
    "name": "Measures to track",
    "contains": "A short set of measures with how often to check them and who owns each."
   },
   {
    "name": "Single points of failure",
    "contains": "Jobs that depend on one person, vendor or system, and the backup each one needs."
   }
  ]
 },
 "output_shape": "PROCESS REVIEW\n  Process: <name> | Goal: <goal> | Scope: <in and out>\n\nPROCESS MAP\n  Suppliers: <who feeds it> | Inputs: <what triggers it>\n  Steps: <1. step, who, time> <2. step, who, time>\n  Outputs: <what it produces> | Customers: <who receives it>\n\nBASELINE\n  <measure> | <today's figure> | <source> | <missing, how to collect>\n\nRANKED PROBLEMS\n  <rank> | <problem> | <evidence> | <root cause> | <owner role> | <effort small, medium or large, with reason>\n\nFIX OPTIONS\n  <fix> | <problem it solves> | <effect> | <effort> | <how to pilot and measure>\n\nMEASURES TO TRACK\n  <measure> | <how often> | <owner role> | <target, if you gave one>\n\nSINGLE POINTS OF FAILURE\n  <person, vendor or system> | <what breaks if it fails> | <backup needed>\n\nCHECKS STILL NEEDED\n  <item> | <who confirms>",
 "how_to_use": [
  "Add the pack as a skill, or paste SKILL.md and then references/source-agent.md into a new chat.",
  "Describe the process step by step, as it runs today, not as it should run. Add the numbers you have, even rough ones.",
  "Pick one job per run, such as \"Review this process\" or \"Draft the procedure for it\". With no numbers yet, ask for a quick pass: it maps the steps and lists the numbers to collect first.",
  "Read the baseline section first. If key numbers are missing, collect them for a week before you act on the fixes.",
  "Check each root cause against what your team knows. Ask the people who do the work if the map matches.",
  "Pilot one fix, measure it against the baseline, then decide whether to roll it out."
 ],
 "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": "Process change note writer",
   "url": "https://useaiblocks.com/prompts/process-change-note-writer",
   "why": "Process change note writer"
  },
  {
   "name": "Process handover guide writer",
   "url": "https://useaiblocks.com/workflows/make-a-recurring-process-easier-to-hand-over",
   "why": "Process handover guide writer"
  }
 ],
 "source": {
  "by": "Michael Sitarzewski and Agency Agents contributors",
  "repo": "msitarzewski/agency-agents",
  "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/specialized/operations-manager.md",
  "licence": "MIT",
  "original_name": "Operations Manager",
  "commit": "b37b5bb33b78f2c1d6567d98e25ca818e3259219"
 },
 "credits": [
  {
   "title": "Operations Manager",
   "by": "Michael Sitarzewski and Agency Agents contributors",
   "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/specialized/operations-manager.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-operations-manager",
  "markdown": "https://useaiblocks.com/agents/agency-operations-manager.md",
  "json": "https://useaiblocks.com/agents/agency-operations-manager.json",
  "instructions": "https://useaiblocks.com/skills/agency-operations-manager/SKILL.md",
  "download": "https://useaiblocks.com/skills/agency-operations-manager.zip",
  "api_item": "https://useaiblocks.com/api/v1/items/agency-operations-manager",
  "api_document": "https://useaiblocks.com/api/v1/documents/agent/agency-operations-manager",
  "mcp": "https://useaiblocks.com/mcp"
 }
}
