Hire an AI failure cause and repair planner

Everything it can hand back

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

• A class of failure, a trigger rule, who must attend, a moderator and ground rules
• A chain of whys with evidence at each level and a cause you can change
• One fix at each level, sized to the pain, with an owner, a date and a check
• A recurrence rule and a plain-words write-up for the team

How it does the job well

• Base people decisions on job-related evidence, applied the same way to everyone.
• Write in plain, respectful language the person affected could read.
• Keep personal data to what the task needs, and handle it privately.
• Check local employment law and company policy before advising on hiring, pay or exits.

Mistakes it avoids

• Biased wording in job ads, reviews or interview questions.
• Plans with no owner, timing or way to check progress.
• Treating a template as legal advice.

What a good result looks like

An example, not your task: Something broke or missed its date and you want to stop it happening again.

• Step 1: The review plan. The failure class, trigger rule, who attends and why, a moderator, ground rules, the line for blame and an agenda.
• Step 2: The chain of whys. Each why with its answer and evidence, a second branch, a cause you can change and a prevention check.
• Step 3: Fixes in proportion. The pain band and one fix per level with size, owner, date, done-when and check, plus a recurrence rule.
• 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

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• 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 Eric Ries would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Plans the review. Narrows the target, writes a trigger rule, lists who must attend, names a moderator and sets the rules and the line for when blame starts.
• Asks why. States the problem as something seen, asks why from facts, tries a second branch and stops at a cause you can change.
• Sizes a fix to each level. Rates the pain, writes one fix per level, makes sure the deep levels get a small first step and adds owners, dates, checks and a recurrence rule.

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 failure-root-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/failure-root-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

• What went wrong, when, who noticed and how often it has happened
• The people and teams involved, and how much they trust one another (optional)
• Logs, messages or customer comments (optional)
• How much it hurt (customers affected, time or money lost, optional)

Tools and access

• Any good chat AI: Setting up the review and writing the agenda is text work.
• A shared calendar: Holds the review slot and the trigger rule.
• 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.
• Any good chat AI: Pairing causes with fixes and writing the review is text work.
• A shared task list: Keeps owners, dates and checks visible until they are done.

Functions and deliverables

• Failure cause and repair planner: Plan a no-blame review, test the chain of causes against facts and assign fixes sized to the actual problem.
  • A class of failure, a trigger rule, who must attend, a moderator and ground rules
  • A chain of whys with evidence at each level and a cause you can change
  • One fix at each level, sized to the pain, with an owner, a date and a check
  • A recurrence rule and a plain-words write-up for the team
• Five whys session planner: Plan a five whys review after a failure. Give it what went wrong and get who must attend, a trigger rule, ground rules and a no-blame agenda.
  • One class of failure and a trigger rule
  • A list of who must attend and why
  • A moderator and ground rules
  • A one-page agenda
• 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 response planner: Turn a chain of whys into a proportional fix plan. Each level gets a fix sized to the pain, with an owner, a date and a check.
  • One fix at each level of the chain
  • Sizes matched to the pain
  • An owner, a date and a check for each fix
  • A plain-words write-up for the team
• 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
• 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
• Eric Ries: Turn a product plan into testable guesses using Eric Ries’s public approach. Start with the riskiest assumption and measure what customers actually do.
  • Your problem worked on the way Eric Ries would: their questions, their method, their push-back
  • The answer or the work, in Eric Ries'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

• Something broke or missed its date and you want to stop it happening again.
• Your last review ended with one person being blamed.
• Someone wants a full rebuild after a small failure.

Limits to check before starting

• You have one small slip that needs no review: write a simple fix-it note, or just fix it and tell the team.
• You want to blame one person: use a talk with their manager instead, because this review stays on the process.
• You need to calm a disagreement: use the Disagreement response writer, not a failure review.

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 plus one skill file for each step.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md". Claude Code and Claude Projects can need a paid plan. In any chat, you can instead paste HANDOFF.md and then each skill file, one after another.
• Describe the failure in a few lines and name the people involved. Send the plan to attendees before the review.
• Share the write-up with everyone, and check each fix on its date.

Read it as data

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