Hire an AI process waste and root-cause reviewer

Everything it can hand back

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

• A table of steps with work time and wait time
• Each step marked value or waste, with the kind of waste named
• The worst waste, backed by the time line, and the step to delete or change first
• A chain of whys with evidence at each level, and a second branch in case there is more than one cause
• The root cause your team can change, a fix and a check that it stays fixed

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.
• Roadmaps with dates but no owners or confidence levels.

What a good result looks like

An example, not your task: A process feels slow and you can't say which steps are the problem.

• Step 1: Process waste map. Each step with work and wait time, marked value or waste, the worst waste, who asked for each step and one change to try.
• Step 2: Root cause. The problem as seen, the records checked, a chain of whys with evidence, a second branch, and the fix with a check.
• Hand-back summary. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Every step in the map has a who, a work time and a wait time, or is marked missing.
• Each why is backed by a record or something seen, not a guess. A why with no record is marked unchecked.
• The root cause is something your team can change, not a person's character, and a second branch was checked.
• Each step ran in order and used the file from the step before, or the run stopped at the step that failed and says 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 Taiichi Ohno and Elon Musk would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Lays out the steps. Lists each step with who does it, how long it takes and how long it waits, from the customer's order to cash in hand.
• Marks value and waste. Marks each step as value or waste, names the kind of waste and finds the worst one.
• Asks who required each step. Lists who asked for each step, questions each requirement and picks one change to try.
• States the problem. Takes the worst waste and the problem you gave, and states it as something seen, with the place and date.
• Asks why, with evidence. Asks why of each answer and checks it against a record, not a guess, until it reaches a cause you can fix.
• Tries a second branch. Follows a second chain in case there are two causes, then writes the fix and how to check it held.

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 process-waste-cause 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/process-waste-cause/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

• Your process, step by step, with who does each step
• Times for work and waiting (optional)
• Where it hurts, or the problem that keeps coming back, with the place and date
• Logs, tickets, photos or notes (optional)
• What was tried before (optional)

Tools and access

• Any good chat AI: Sorting steps and ranking waste is text work.
• A spreadsheet: Adds up work and wait time and shows the share.
• Any good chat AI: Building and checking a chain from records is text work. Claude, ChatGPT and Gemini all do it with this skill.
• Your ticket or incident system: Holds the logs and tickets the chain needs as proof. Copy in the lines that matter.

Functions and deliverables

• Process waste and root-cause reviewer: Share the process steps and real observations. Get likely waste, a change to try and a cause review with evidence gaps.
  • A table of steps with work time and wait time
  • Each step marked value or waste, with the kind of waste named
  • The worst waste, backed by the time line, and the step to delete or change first
  • A chain of whys with evidence at each level, and a second branch in case there is more than one cause
  • The root cause your team can change, a fix and a check that it stays fixed
• Process waste finder: Find waste in a slow process. Paste your steps and times. You get each step marked value or waste, the worst waste named and one change to try.
  • A table of steps with times
  • Each step marked value or waste with a named kind
  • The worst waste, backed by the time line, with where its mistakes travel
  • One change to try, and a review date
• Root cause finder: Find the root cause of a problem that keeps coming back. Get a chain of whys checked against facts, a fix and a prevention check.
  • The problem written as something seen, not a guess
  • A chain of whys, each answer with its proof or marked unconfirmed
  • A second chain, in case there is another cause
  • The root cause your team can change
  • A fix that removes it, and a prevention check
• 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
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.
• Taiichi Ohno: Review workflow waste or a recurring defect using Taiichi Ohno’s recorded approach. Observe the work, inspect handoffs and plan one small improvement test.
  • Your problem worked on the way Taiichi Ohno would: their questions, their method, their push-back
  • The answer or the work, in Taiichi Ohno's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Elon Musk: Question a cost or process using Elon Musk’s recorded approach. Break down the parts, challenge requirements and simplify before trying to automate.
  • Your problem worked on the way Elon Musk would: their questions, their method, their push-back
  • The answer or the work, in Elon Musk'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

• A process feels slow and you can't say which steps are the problem.
• The same mistake keeps happening, and each fix lasts only a few weeks.
• You inherited a process and want to know which steps can be deleted.

Limits to check before starting

• You have no process yet and want to design one: write the main steps down on paper first, then come back.
• You need to set prices or pick a strategy: use the Brand and sales budget splitter.
• You have one single mistake to explain and no process steps: ask a colleague who saw it to walk you through what happened.

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's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your process with who does each step and the times. The result depends on these most. Add the problem with its place and date.
• It works step by step and saves each result.
• Go and look at the real place or record for any why it can't check, then bring back what you find.
• Make the one change to the worst waste first. After it, run the waste map again to find the next worst waste.

Read it as data

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