Hire an AI business quality and return reviewer

Everything it can hand back

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

• The edge and the barrier around it, with the kinds of scale that apply
• A sort of the business into yes, no or too tough, with your real edge written down
• Who keeps the gain from any improvement, and how rivals behave
• Ratings for able, honest and owner-minded managers, each with its evidence
• The long-hold sums and a keep, wait or pass call with the figures that would change it

How it does the job well

• Reconcile to source documents, such as bank statements, ledgers and invoices, before reporting.
• Show the calculation, inputs and period for every figure.
• Label actuals, estimates and forecasts clearly.
• Send tax, legal and regulatory questions to a qualified professional.

Mistakes it avoids

• Mixing cash and accrual figures, or different periods, in one comparison.
• Rounding or formula errors that do not tie back to totals.
• Giving personal investment advice.

What a good result looks like

An example, not your task: You are studying a business to own for years and want to know if it is a great one before you look at price.

• Business power tester. What customers get that rivals cannot match, the barrier that protects it, and the kinds of scale at work.
• Circle of competence sorter. Your five answers, your real edge or none, and a yes, no or too tough sort.
• Who-keeps-the-gain tester. Whether gains stay with owners or pass to customers and rivals, and if the industry is commodity, brand-led or protected.
• Owner-minded management checker. A log of what managers did with cash and ratings for able, honest and owner-minded.
• Long-hold return calculator. The long sums, a comparison with your next best choice, and a keep, wait or pass call.
• 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 Charlie Munger and Warren Buffett would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Tests the edge and the wall. Names what customers get that rivals cannot match, the barrier that protects it and the kinds of scale at work, and checks the opposite pull of size.
• Checks you can judge it. Asks five plain questions you answer without notes, writes down your real edge and sorts the business as yes, no or too tough.
• Asks who keeps the gain. Runs a two-line sum on each improvement, with and without rivals getting it, and sorts the industry as commodity, brand-led or protected.
• Rates the managers. Logs what they did with spare cash, compares pay with owner results and rates able, honest and owner-minded from the record.
• Runs the long sums. Shows how the business return caps the owner's, how entry price shifts it and what tax timing costs, then compares with your next best choice.

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 great-business-judge 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/great-business-judge/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 business, what it sells and who its main rivals are
• What you know about it and your own background in the field
• Any figures, such as returns on the money invested, price history and what managers did with cash (optional)
• The changes to test, such as a cost cut or a better product
• Your tax rate and your next best choice for the money (optional)

Tools and access

• Any good chat AI: Weighing evidence against a fixed list of tests is reasoning work any strong chat AI does well.
• Your accounts or margin report: Real margins make the materiality test a number, not an opinion.
• Any good chat AI: Sorting honest answers against fixed rules is text work any strong chat AI does well.
• A notebook: Writing your five answers by hand, without a search tab open, makes the test honest.
• Claude, ChatGPT or Gemini: The sums are simple and the sorting is text work any strong chat AI does well.
• A spreadsheet: Lets you rerun the two-line sum with your own price and cost figures.
• Any good chat AI: Reading a record of choices and rating them against fixed rules is text work any strong chat AI does well.
• A spreadsheet: Lets you tabulate years of deals and payouts to see a pattern.
• A spreadsheet: Lets you rerun the compounding with your own years and rates and check every line.
• Any good chat AI: It can lay out the cases and weigh them, but check the arithmetic against a calculator.

Functions and deliverables

• Business quality and return reviewer: Share company records, rival facts and your own experience. Get a review of the business, its leaders and possible returns, with gaps marked.
  • The edge and the barrier around it, with the kinds of scale that apply
  • A sort of the business into yes, no or too tough, with your real edge written down
  • Who keeps the gain from any improvement, and how rivals behave
  • Ratings for able, honest and owner-minded managers, each with its evidence
  • The long-hold sums and a keep, wait or pass call with the figures that would change it
• Competitive advantage tester: Share your business, rivals and cost or price evidence. Get a test of the benefit, copying barrier and seven possible sources of advantage.
  • The benefit named in numbers and the barrier in words
  • A materiality test with a number or a clear reason
  • A match to one of the seven powers, and the stage check
  • The edge to build next and the evidence still missing
• Business expertise reviewer: Describe a business or bet. Get it sorted as yes, no or too tough, with your real edge written down.
  • Five answers marked as known, guessed or blank
  • Your real edge written down, or "no edge"
  • A sort into yes, no or too tough, with the reason
  • The first question you cannot answer, and a plan to widen the circle if it is worth it
• Business value capture reviewer: See if a cost cut or new machine stays with the owner or goes to customers. Get two sums, an industry sort and a verdict.
  • A two-line sum for each change: what the owner keeps if only this business gets it, and if every rival does
  • How rivals behave, with an example
  • The industry sorted as commodity, brand-led or protected, with the reason
  • Which way technology cuts
  • A one-line verdict on whether gains tend to stick, leak or are contested
• Company management record reviewer: Share leaders’ cash decisions, pay and letters. Get evidence-based ratings and gaps, viewed alongside the underlying business.
  • A cash log marked good, poor or unknown
  • A comparison of pay with owner results
  • Ratings for able, honest and owner-minded, each with its evidence
  • A call, and the one fact that would change it
• Long-run business return calculator: Paste what you know about a business and its price. Get the long-run sums and a keep, wait or pass call.
  • A low, middle and high case for the business return
  • The cap sum, the price grid and the tax sum with your figures
  • Your real alternative set as the bar
  • A keep, wait or pass call and the figures that would change it
• 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
• 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
• Warren Buffett: Review a business using Warren Buffett’s recorded principles. Check how it earns, what protects it, how managers use cash and which facts remain uncertain.
  • Your problem worked on the way Warren Buffett would: their questions, their method, their push-back
  • The answer or the work, in Warren Buffett'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 are studying a business to own for years and want to know if it is a great one before you look at price.
• A business looks cheap, and you want to know if it is cheap for a good reason.
• You like a business as a customer and want to test that against how it earns.

Limits to check before starting

• You want a buy or sell call on a listed stock or a trade: this gives no calls on named securities, so use a licensed financial adviser.
• You only want to know if a price is too high after you like the business: use the Bet price and odds reviewer.
• You cannot study the business in depth, such as a firm with no public facts: ask someone who knows the field first, then come back.

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 holds HANDOFF.md plus one skill file for each step.
• Open Claude Code, or a Claude Project where you can add files. Give it the folder and say "Follow HANDOFF.md".
• Gather the business facts, at least five years of return on invested money, what managers did with cash, your tax rate and your next best choice. Say plainly what you have done in the field.
• Let it run one step at a time. It saves each result as a file before the next step starts.
• Read the circle of competence result before the final call. If it says too tough, treat the call with care.
• The figures are yours, and the call rests on them. Any figure not checked against the company's annual reports is marked unverified.
• The call judges the business, not your money. It does not know your savings, debts or goals, so it is not advice to buy, sell or keep anything.
• Check the HAND-BACK SUMMARY for MISSING lines. Fill those gaps and rerun the steps that need them.

Read it as data

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