Hire an AI project investment decision reviewer

Everything it can hand back

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

• Each bet called near cinch, fair bet or no bet, from the payoff sum at three estimates
• One to three picks ranked and sized, with a written no for the rest
• Who is paid to steer you and where it pulls the wrong way
• Whether the plan survives a bad year, with a score and fixes
• A one-page rule set with facts to watch, review dates, the cost of acting and the only reasons to act

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 have more ideas than you can back and no clear way to choose.

• Mispriced bet tester. Each bet called near cinch, fair bet or no bet, from the payoff sum at your low, middle and high estimates.
• Twenty-punch bet ranker. A scored list, one to three sized picks, and a written reason for every bet you drop.
• Incentive checker. Who is paid to steer you, how they are paid, and where that pulls the wrong way.
• Room for error plan checker. The point of ruin, a bad-year test result, a score out of 100 and fixes.
• Sit-still rule writer. Facts to watch, fixed review dates, the cost of acting and the only reasons to change course.
• HAND-BACK SUMMARY. Each step's file, any step not run, 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 odds after the price. Turns each price into the chance the crowd gives, runs chance times payoff at three estimates and calls each bet near cinch, fair bet or no bet.
• Ranks on a twenty-punch card. Scores understanding, edge and survivability, compares each with your next best use, keeps one to three and sizes them.
• Checks who profits from steering you. Lists who is selling, how each is paid and where it pulls the wrong way, with a warning for big commissions.
• Checks you survive a bad year. Finds the point of ruin on the sized plan and fixes the size until you can stay in.
• Writes the rules for sitting still. Lists the facts that must stay true, fixed review dates, the cost of acting and the three reasons to change course.

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 few-big-bets 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/few-big-bets/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 bets you are weighing, with what goes in, what each pays and what you lose if it fails
• The price or odds for each one, if there are any
• Your range for how likely each is, and why you think so
• The pot, what must stay safe, your fees and tax rate (optional)

Tools and access

• Any good chat AI: Turning prices into odds and running the sums is text work any strong chat AI does well.
• A spreadsheet: Lets you rerun the payoff sum with your own figures.
• Any good chat AI: Scoring and ranking against fixed rules is text work any strong chat AI does well.
• A notebook: A paper card with twenty boxes makes each commitment feel real.
• 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: Stress-testing a plan in words and simple sums is text work.
• A spreadsheet: Lets you rerun the plan with a bad year and see cash by month.
• Any good chat AI: Turning picks into a fixed template and doing simple cost sums is text work any strong chat AI does well.
• A calendar: Put the review dates in as repeating events so you look on those days and no others.

Functions and deliverables

• Project investment decision reviewer: Rank major ideas and check who gains from the advice. Review downside risk, then draft how much to commit and when to act.
  • Each bet called near cinch, fair bet or no bet, from the payoff sum at three estimates
  • One to three picks ranked and sized, with a written no for the rest
  • Who is paid to steer you and where it pulls the wrong way
  • Whether the plan survives a bad year, with a score and fixes
  • A one-page rule set with facts to watch, review dates, the cost of acting and the only reasons to act
• Bet price and odds reviewer: Test your bets against their price. Give each bet a cost and payoff and get a call of near cinch, fair bet or no bet, with the odds.
  • What the price says about the crowd's chance
  • Your range, with the facts behind it
  • The payoff sum at low, middle and high
  • Each bet called near cinch, fair bet or no bet, with what would change it
• Investment priority planner: Rank your bet ideas with a twenty-punch card. Get one to three sized picks and a written no for the rest, so you stop spreading thin.
  • A scored list on understanding, edge and survivability
  • One to three picks in order, each with the alternative it beats
  • Sizes with a survival limit and what each pick must not risk
  • A written no for every other idea
• 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
• Business plan risk buffer reviewer: Check your budget or business plan for room for error. Get a survival score out of 100, where it breaks in a bad year, and fixes.
  • A list of what must go right for the plan to work
  • Three believable ways it fails, each with a number or a date
  • The ruin point and a score out of 100 for how well the plan survives
  • Fixes sized to the worst case, and one rule against a panic move
• Investment holding rule writer: Write sit-still rules for your investments: the facts that must stay true, fixed review dates, what acting costs you, and the only reasons to act.
  • Two to four checkable facts for each pick
  • Fixed review dates and a holds, weaker or broken marking
  • A cost-of-acting line with numbers
  • Three reasons to act, the reasons that do not count, and a cooling line
• 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 have more ideas than you can back and no clear way to choose.
• You tend to spread thin, check often and change your mind with every move.
• Someone is selling you an idea with a big commission and a thick pack of paper.

Limits to check before starting

• You want a buy or sell call on a named stock or fund: ask a licensed financial adviser, as this gives no such calls.
• You only want to know if you have real skill in one area: use the Business expertise reviewer first.
• You want to check whether a single plan survives a bad year: use the Bad-year break-even tester.

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".
• List your bets, with what each costs and pays. Give a low, middle and high chance for each.
• It works step by step and saves each result. Print the last page and put it where you look at your picks.

Read it as data

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