Hire an AI deal and hiring decision reviewer

Everything it can hand back

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

• A map of what you know and don't, with a basket of in, learn first or pass
• A staying-power grade with the protection, the threat and the technology test
• A trust verdict on the people, with questions to ask others
• A value range, a walk-away price and the alternative to beat
• A yes, no or too-hard call, the size of the commitment and what would change it

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: You are about to sign a contract, hire a senior person or buy a business, tool or stake.

• step-01-circle-of-competence-mapper.md. The parts of the deal rated known, partly known or not known, your edge, and a basket of in, learn first or pass.
• step-02-staying-power-checker.md. What protects it, how long a rival needs to copy it, the main threat, the technology test and a grade.
• step-03-people-trust-checker.md. A verdict on the people's ability, honesty, reliability and owner mindset, with questions to ask others.
• step-04-price-against-value-checker.md. A low, middle and high value, a walk-away price and the alternative to beat. Not personal financial advice.
• step-05-failure-first-plan-check.md. What would guarantee failure, the survival risks and the changes to make to the plan.
• step-06-yes-no-too-hard-call-writer.md. A yes, no or too-hard call, the size of the commitment, what would change it and a review date.

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

• Do you understand it?. Splits it into parts, rates each by what you have done, finds the edge and picks a basket.
• Will it last?. Names what protects it, how long a rival needs to copy it, whether that is widening, and what could replace it.
• Can you trust the people?. Tests ability, honesty when it cost them, reliability and owner mindset, and writes questions for people they did not choose.
• Is the price right?. Builds a low, middle and high value, sets a walk-away price and compares it with your best alternative.
• Turns it upside down. Asks what would guarantee failure and checks the plan against the usual ways it fails.
• Makes the call. Applies the yes, no or too-hard rule, compares with your best recent chances and sets the size.

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 four-filter-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/four-filter-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

• What you are considering, in a few lines, and the years that matter
• What you have done, studied or read about the field
• Everything you know about the people involved and how they are paid
• What you would get over time and what it costs
• Your best alternative use of the same money or time (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: 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

• Deal and hiring decision reviewer: Review understanding, lasting value, people and price, then challenge the failure risks and draft a yes, no or too-hard call.
  • A map of what you know and don't, with a basket of in, learn first or pass
  • A staying-power grade with the protection, the threat and the technology test
  • A trust verdict on the people, with questions to ask others
  • A value range, a walk-away price and the alternative to beat
  • A yes, no or too-hard call, the size of the commitment and what would change it
• Knowledge gap reviewer: Describe a topic or decision. Get what you know, half know and don't, and a verdict: in, learn first or pass.
  • The parts you must understand to judge it
  • Your level in each part, with the evidence
  • The edge of what you know
  • A verdict: in, learn first or pass, with the rule for it
• Competitive advantage durability reviewer: Check how long a business, supplier or job path will last. Describe it and get what protects it, what could break it, and a grade.
  • The source of protection, with evidence
  • How long a rival would need to copy it
  • Whether it is widening or narrowing
  • The main threat, a technology test, and a grade: strong, fair or weak
• Working relationship trust reviewer: Share evidence about people behind a deal or hire. Get a review of their record, incentives and what to check next.
  • A rating on ability, honesty, reliability and owner mindset
  • The pay structure and what it bends
  • Questions to ask people they did not choose
  • A verdict: trust, trust with checks or do not trust
• Price against value checker: Share dated cash flows, costs and a rate. Get value scenarios, missing assumptions and a maximum-price rule where the inputs support one.
  • Three supported value scenarios with dated sums, or the gaps that block them
  • An ordered range only when all supported cases fit their original order
  • A maximum-price scenario after the value and order checks, with its rule and limits
  • The stated alternative, friction costs and a before-you-commit list
• 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
• Investment decision brief writer: Turn your four filter results into a clear yes, no or too-hard call, with how big to commit and what would change it. Built for close choices.
  • A call: yes, no or too hard, with the rule that gave it
  • How the choice compares with your best recent chances
  • How big a commitment fits
  • What would change the call, and how you will judge the process
• 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.
• 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 about to sign a contract, hire a senior person or buy a business, tool or stake.
• Someone is pushing you to decide fast on something you only partly understand.
• You want a fixed way to say no, so you stop being talked into things.

Limits to check before starting

• You are making a small, routine purchase: just decide yourself, or ask a friend you trust.
• You only want to know if a price is fair: use the Business asset value estimator.
• You want to check if someone's advice can be trusted: use the Advice credibility checker.

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.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Answer the first step honestly. If it says pass, read the reason before you ask it to carry on.
• Gather the deal details, the years that matter, your track record in the field, how the people are paid and the cost figures before you start.
• Bring the best chances you saw in the last year to the last step, so the call has something to compare with.

Read it as data

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