Hire an AI decision and risk reviewer

Everything it can hand back

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

• The obvious questions settled, with the sums for your target and a smaller question left
• An answer from each field, with where they agree and clash
• The pressures bending your judgment, and who is rewarded for what
• The effects of the effects, the ways the plan could fail, and the best case against it

How it does the job well

• Agree the question and the decision it supports before analysing.
• Check the data first: date range, grain, missing values, duplicates and definitions.
• Compare like with like: same period length, definitions and segments.
• Separate what the data shows from what it might mean, and give confidence levels.

Mistakes it avoids

• Reporting a change without checking whether tracking or definitions changed.
• Treating correlation as cause.
• Averages that hide important segments or outliers.

What a good result looks like

An example, not your task: You face a costly or hard-to-undo decision and only one kind of expert has looked at it.

• step-01-no-brainer-question-settler.md. The obvious questions settled, a rough sum for your target and one to three open questions.
• step-02-mental-model-checklist-runner.md. An answer from each field, where they agree or clash, and the facts still missing.
• step-03-decision-bias-pileup-checker.md. The pressures bending your judgment and a calmer version of the choice.
• step-04-incentive-checker.md. Who is rewarded for what, where it pulls the wrong way, and a fix.
• step-05-second-order-effects-tracer.md. The effects of the effects, how much of the gain you keep, and a revised plan.
• step-06-failure-first-plan-check.md. What would guarantee failure, the survival risks first, and changes that avoid them.

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 Charlie Munger and Charles Darwin would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Settles the obvious first. Lists the big questions, settles the ones with an obvious answer, runs a rough sum on your target and leaves a smaller question.
• Checks many fields. Runs the case through maths, accounting, engineering, physics, biology, psychology and economics, and finds where they agree or clash.
• Finds the pressures on you. Writes your clear reasons first, then looks for rewards, past promises, the crowd and fear of loss, and cools the strongest.
• Checks the rewards. Lists how each person is paid, what that encourages and a fix that cannot easily be gamed.
• Follows the consequences. Traces what the change causes, how people react and how much of any gain you keep. Uses the incentive findings from step 4.
• Turns it upside down. Asks what would guarantee failure and checks the plan against the usual ways it fails.
• Argues the other side. Writes the best case against the plan, marks what you cannot answer and makes a go, change or wait call.

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 mental-models-decision 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/mental-models-decision/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 decision, the result you want and the date you must decide by
• Your reasons for it, in your own words
• The numbers you have, such as money, volumes and time (optional)
• Who is involved and how each is paid (optional)

Tools and access

• Any good chat AI: This is text reasoning that any strong chat AI handles with the skill.
• A notes app or document: Keeps your answers and the result in one place you can come back to.
• Any good chat AI: It is a reasoning task on text that any strong chat AI can do with this skill.
• A trusted second reader: A person outside the situation can spot pressures you cannot see from inside.
• Any good chat AI: It reasons about people, rewards and plans in text, which any strong chat AI handles with this skill.
• A spreadsheet: Easier to try a new pay rule on past numbers and see what it would have paid.
• Any good chat AI: Listing and testing failure modes is text reasoning that any strong chat AI handles with this skill.
• A spreadsheet: Handy for putting numbers on dependencies, cash and runway.

Functions and deliverables

• Decision and risk reviewer: Share the choice, evidence and limits. Get key assumptions, pressures, rewards, possible effects, failure risks and the case against the plan.
  • The obvious questions settled, with the sums for your target and a smaller question left
  • An answer from each field, with where they agree and clash
  • The pressures bending your judgment, and who is rewarded for what
  • The effects of the effects, the ways the plan could fail, and the best case against it
• Simple decision checker: Settle the obvious questions in a big problem, check your target with a rough sum and cross off dead paths. You get a smaller question to solve.
  • The big questions, split into settled and still open
  • A rough sum showing what your target needs
  • The paths the sums rule out
  • A smaller question to carry into the next step
• Decision checklist reviewer: Run a plan through many fields. Get a mental models checklist answer from each, where they stack or clash, and the facts you still need.
  • A short answer from each field, rated for, against or neutral, with how sure it is
  • The places where two or more fields agree and the result could be extreme
  • The clashes and the trade-off each one creates
  • The three facts to find next, and the field you leaned on too much
• Decision bias checker: Check a decision for pressure before you commit. Describe it and get the pressures bending your judgment, plus a calmer version of the choice.
  • Your rational case, written before the pressure check
  • The pressures present, each tied to a fact in your situation
  • A flag when three or more stack, with a cooling-off step
  • A calmer version of the choice, and a rating of how much to trust your gut
• Incentive checker: Check your pay plan or deal with this incentive checker. See who is rewarded for what, where it pulls the wrong way, and get a fix.
  • A table of people, rewards and the behaviour each really encourages
  • Each mismatch with a concrete example
  • A fix that pays for the outcome you want, with a loophole check
  • A note on pay fairness and on which work is routine and which is thinking
• Decision consequence planner: Trace the second-order effects of a price, pay or rule change. Get the reactions, the gaming risks and how much of the gain you keep.
  • The direct effects, then the reactions, then the effects of those
  • A list of how people could game the new rule
  • How much of any gain you keep, and how much flows away
  • A revised plan that allows for the reactions
• Plan failure reviewer: Find the ways your plan could fail before you commit. Paste your plan and goal, and get ranked failure risks with a fix for each.
  • The goal in one line
  • A list of failure modes specific to your plan, survival risks first
  • A change to the plan for each failure
  • The bet stated, and a set of attacks for the people you pick to argue against it
• Plan objection writer: Share a plan and your reasons. Get the strongest objections, a test for changing your mind and a decision call.
  • The best three arguments against you, in the opponent's words
  • The facts behind each, and which you can answer
  • The assumption of yours that is hit hardest
  • What would change your mind, and a call: go, change or wait
• Metric definition writer: Share a metric, calculation and business use. Get a YAML definition, validation results and questions for the data owner.
  • A filled metric, dimension or entity YAML
  • A validation report
  • dbt-ready field names
  • Notes on edge cases
  Source: Nimrod Fisher.
• Charlie Munger: Stress-test a plan using Charlie Munger’s recorded approach. Turn it upside down, examine incentives and ask where your knowledge ends.
  • Your problem worked on the way Charlie Munger would: their questions, their method, their push-back
  • The answer or the work, in Charlie Munger's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Charles Darwin: Build a case using Charles Darwin’s recorded approach. Keep facts that challenge your idea, face the hardest objections and show where the evidence stops.
  • Your problem worked on the way Charles Darwin would: their questions, their method, their push-back
  • The answer or the work, in Charles Darwin'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

• You face a costly or hard-to-undo decision and only one kind of expert has looked at it.
• A choice feels close and you want to know what you are missing before you commit.
• You are very sure about a plan and want to test it before you spend money on it.

Limits to check before starting

• You face a small choice that is easy to undo: make a simple pros-and-cons list instead.
• A clear rule already settles the decision: follow the rule, or ask one expert.
• You only want the strongest argument against your plan: use the Plan objection writer.

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".
• Describe the decision and give your reasons before you read any of its findings.
• Read the last step first. If a key argument is still open, wait before you act.

Read it as data

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