Hire an AI decision review checklist editor

Everything it can hand back

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

• A log of mistakes sorted by cause, with the repeat offenders
• A one-page checklist of twelve questions or fewer, each with a pass line, tested on your past cases
• A live decision answered item by item, with a call and a record
• An edited list, a version log and practice cases

How it does the job well

• Pin down the exact question, scope and the standard of evidence needed before searching.
• Prefer primary sources, and say how strong each source is.
• Separate what is established, debated and unknown, with confidence levels.
• Cite specifically: author, work, date or page where possible.

Mistakes it avoids

• Presenting one source or a popular claim as settled.
• Inventing citations, quotes or page numbers.
• Over-generalising across places, periods or groups.

What a good result looks like

An example, not your task: You make the same kind of decision often, such as hiring, pricing or taking on clients.

• Step 1: Mistake log. Every past case sorted as good call, bad luck, lucky win or mistake, with causes, catching questions and repeat offenders.
• Step 2: The checklist. A one-page list of twelve questions or fewer, each with a pass line, tested on two past mistakes.
• Step 3: The live run. Each item answered with a fact and marked pass, fail or unknown, then a call and a record to judge later.
• Step 4: Upkeep. The call judged by its process, an edited checklist, a version log, practice cases and review dates.
• 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 Ray Dalio would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Logs the mistakes. Sorts past cases into good call, bad luck, lucky win or mistake, names the cause of each mistake and counts the repeats.
• Builds the list. Writes stop items first, turns repeat causes into yes/no questions with pass lines, and cuts to twelve items or fewer.
• Tests it on the past. Runs the list on two logged mistakes to check it would have caught them, and fixes it if it did not.
• Runs it live. Answers every item with a fact, counts unknowns as fails, applies the stop rule and records the call.
• Judges by process. After the result, compares the record with what happened and sorts the call by how it was made, not only by how it ended.
• Keeps it sharp. Adds, sharpens or cuts items, keeps a version log and writes practice cases and review dates.

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 decision-checklist 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/decision-checklist/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 kind of decision you keep making
• Three or more past cases of yours, with what you chose and what happened
• Cases from other people in the same field (optional)
• Later, a live decision to run, and the result once it is known

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 the log, the checklist and your records in one place you can come back to.

Functions and deliverables

• Decision review checklist editor: Use past mistakes to build a one-page checklist, apply it to a real decision and improve it when the result is known.
  • A log of mistakes sorted by cause, with the repeat offenders
  • A one-page checklist of twelve questions or fewer, each with a pass line, tested on your past cases
  • A live decision answered item by item, with a call and a record
  • An edited list, a version log and practice cases
• Decision mistake collector: Log past decisions and outcomes. Get repeated causes, evidence limits and a prompt to interrupt the pattern next time.
  • Each case sorted: bad process, bad luck, lucky win or good call
  • A cause named for each real mistake
  • The causes that repeat, with a count
  • For each case, the question that would have caught it
• Decision checklist builder: Turn your mistake log into a decision checklist: up to twelve yes/no questions, each with a pass line, tested on two past cases.
  • A one-page checklist of twelve or fewer yes/no questions
  • A pass line and a place to find the answer for each
  • Stop items first, then cheap checks, then costly ones
  • A test of the list against two past cases
• Decision checklist runner: Run your checklist on a real decision. Each item gets a fact, a pass, fail or unknown, then a clear go, wait or no call.
  • Each item answered with evidence, marked pass, fail or unknown
  • Which stop items failed, if any
  • The call: go, wait or no, with a reason
  • A record of what you expect and what would show you wrong
• Checklist review planner: Share a decision record, the result and your checklist. Get a separate review of process and outcome, checklist changes and practice cases.
  • The call judged on process and outcome separately
  • Which items fired, which were missing, and what to add or cut
  • A version log of the changes
  • Three practice cases and a review schedule
• Research paper and code note writer: Share a paper, repo or messy notes. Get claims, methods and evidence sorted into a clear research folder.
  • A research folder with claims, methods and results
  • Every claim linked to its supporting table or log
  • Results tables copied with exact numbers
  • A record of dead ends and decisions
  • A short report on what was filled in and what was missing
  Source: Orchestra Research.
• 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
• Ray Dalio: Review a choice or a mistake using Ray Dalio’s recorded approach. Set the goal, hear other views and draft a rule to test.
  • Your problem worked on the way Ray Dalio would: their questions, their method, their push-back
  • The answer or the work, in Ray Dalio'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 make the same kind of decision often, such as hiring, pricing or taking on clients.
• You keep paying for the same mistake in a different form.
• A team needs a shared list so that its decisions do not depend on who is in the room.

Limits to check before starting

• You face a one-off decision with no repeats: ask a trusted adviser or write a simple pros and cons list instead.
• You have no past cases to look back on: start by writing down your next few decisions and what you knew at the time, then come back.
• You only want a quick opinion on a single choice today: ask your AI directly rather than build a full list.

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".
• Give the first two steps your honest past cases, including the ones you would rather forget. Then print the checklist.
• Use the list on your next real decision. When the result is known, bring the saved record back for the last step.

Read it as data

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