Hire an AI operations manager

Everything it can hand back

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

• 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

How it does the job well

• Baseline first. Never claim a gain you cannot measure. "It feels faster" is not a result.
• Root cause, not symptom. A fix that only masks a defect counts as failure.
• Standardize before you optimize. An undocumented, unstable process cannot be improved yet. Write it down first.
• System, not silo. Check the effect on the end-to-end flow.
• Vendors need measurable service levels. Flag any vendor managed on goodwill.
• Measure before you change, measure after. Every improvement needs a baseline and a post-change metric. "It feels faster" is not a result; never claim a gain you can't quantify.
• Find the root cause, not the symptom. Use structured root-cause analysis before recommending a fix. Adding people, steps, or inspection to mask a process defect is treated as failure, not solution.

Mistakes it avoids

• Losing commitments buried in long notes.
• Mixing confirmed facts with guesses about other people's plans.
• Adding process when a short checklist would do.

What a good result looks like

An example, not your task: Orders, tickets or invoices are late, and you do not know which step is the cause.

• Process map. Who feeds the process, the steps in order with owners and times, and who receives the result.
• Baseline. The figures you have today and the measures that are missing, with how to collect them.
• Ranked problems. Each bottleneck with its evidence, root cause, owner role and a rough effort rating.
• Fix options. Fixes sorted by effect and effort, each with how to pilot and measure it.
• Measures to track. A short set of measures with how often to check them and who owns each.
• Single points of failure. Jobs that depend on one person, vendor or system, and the backup each one needs.

How the work is checked

• Every action has an owner and a date, or is marked as missing one.
• Each item points to the note or message it came from.
• The output fits where it will be used, such as one screen or one page.
• 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 Ed Catmull would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Set the boundary. It lists who feeds the process, what goes in, the main steps, what comes out and who receives it. Gaps are asked once, then marked MISSING.
• Map the current steps. It lays out each step with who does it, how long it takes and where work waits.
• Set the baseline. It records today's time, volume and error figures, and lists the measures you need but lack.
• Find waste and the bottleneck. It marks waiting, rework, handoffs, extra checks and idle skills, and names the step that limits the whole flow.
• Trace root causes. It asks why, step by step, until a cause is backed by evidence from your description or numbers.
• Rank fixes and set controls. It sorts fixes by effect and effort, picks measures and owners, and flags single points of failure.

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 operations-manager 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/operations-manager/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 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)

Helpful context (optional)

• A task list or ticket export with start and finish dates, so cycle times are real, not guessed.
• A short interview note from the person who does the job each day.

Tools and access

• Claude, ChatGPT or Gemini with file upload: They can read an exported spreadsheet of tickets or orders and work out time and error figures from it.

Functions and deliverables

• Operations manager agent: Find where your process wastes time and why. Get a ranked list of bottlenecks with evidence, root causes, measures to track and fixes.
  • 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
  Source: Michael Sitarzewski and Agency Agents contributors.
• Problem root cause tracer: Find the root cause behind problem notes on your work. Paste the notes. You get likely causes ranked, plus notes that may point at the wrong spot.
  • Each problem with whether the spot holds up on its own
  • Likely causes upstream, grouped, with a hold-test answer for each
  • A list of notes that may name the wrong symptom
  • A first quick check for each top cause, and what result would prove it
• Process bottleneck finder: Describe the process and any timing data. Get a swim-lane map, cycle-time estimates and likely bottlenecks ranked.
  • A swim-lane process map
  • A ranked list of bottlenecks
  • Cycle time figures per stage
  • A root-cause guess for each bottleneck
  • The share of time spent on real work
  Source: Alireza Rezvani.
• Agent tool designer: Describe the agent’s jobs and tool problems. Get clear tool definitions, input and output rules, examples and recovery errors.
  • A shorter, clearer tool list
  • A description for each tool
  • Better error messages
  • A naming and settings pattern to follow
  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
• Ed Catmull: Plan feedback or protect rough creative work using Ed Catmull’s recorded approach. Name the problem, keep the creator’s choice and find hidden issues.
  • Your problem worked on the way Ed Catmull would: their questions, their method, their push-back
  • The answer or the work, in Ed Catmull'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

• 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.

Limits to check before starting

• 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.

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 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.

Read it as data

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