Hire an AI project decision reviewer

Everything it can hand back

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

• A call to push on, change course or stop, with a reason and a date
• The three strongest arguments against that call and which ones you can answer
• The loss you could not recover from and a way to cap it
• How much proof is enough, the first fact to get and a date to decide

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 have thought about quitting for weeks and keep going back and forth.

• Step 1: The call. Facts, effort test, prize test, evidence versus fear, cost of staying, and one call with a date.
• Step 2: The case against. Your opponent's three best arguments, each marked answered or open, plus the weak assumption and what would change your mind.
• Step 3: The loss cap. What the plan depends on, the loss you could not recover from, fixes with cost and an early warning sign.
• Step 4: The evidence bar. How reversible the choice is, how much proof is enough, the first fact to get and the date to decide.
• 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 Charles Darwin and Benjamin Franklin would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Call it dip or dead end. Gets the facts, tests whether more effort ever raised results, asks if getting through would make you best at something worth it, splits evidence from fear and makes one call with a date.
• Argue the case against the call. Picks the sharpest opponent, writes their three best arguments, answers each or marks it open, names the weak assumption and sets what would change your mind.
• Cap what you can lose. Lists what the plan depends on, finds the outcome you could not recover from, adds a fix that caps each such loss with its cost and names a sign to act early.
• Set the evidence bar and a date to decide. Says how reversible the choice is, weights the facts you wish you had, sets how much proof is enough and names the cheapest fact to get first.

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 decide-whether-to-quit-a-project-and-set-the-evidence-bar 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/decide-whether-to-quit-a-project-and-set-the-evidence-bar/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 project, its start date and what you have put in
• What results you have had and when
• Your reasons to stay and to quit, honest and unsorted
• What is at stake if it fails, such as money, time or your name

Tools and access

• Any good chat AI: Weighing a list of reasons and facts is text work any strong chat AI does well.
• A spreadsheet: A simple sheet of results by month shows the trend the skill needs.
• 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 dependencies and testing plans in text is what any strong chat AI does with this skill.
• A spreadsheet: Handy for putting fixed costs, cash and exposure side by side.
• Any good chat AI: Weighting facts and doing the share sum is text work any strong chat AI does well with this skill.

Functions and deliverables

• Project decision reviewer: Review whether to keep going, change or stop. Test the opposing case and set loss limits, evidence and a date to decide.
  • A call to push on, change course or stop, with a reason and a date
  • The three strongest arguments against that call and which ones you can answer
  • The loss you could not recover from and a way to cap it
  • How much proof is enough, the first fact to get and a date to decide
• Project decision checker: Tell it which project you want to quit. Get one call, push through, change course or stop, with your evidence and your fears set apart.
  • One call: push through, change course or stop, with the reason
  • Your reasons split into evidence, fear and wish to settle for less
  • What you would be best at if you got through, and how you could check it
  • A check date, and one hard step if you push on
  • A way to quit well, if the call is to stop
• 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
• Ruin risk stress tester: Check your plan for ruin risk. Paste it in and find the one outcome you could not recover from, plus a version with the downside capped.
  • A list of dependencies and things that could go wrong, with no odds guessed
  • The outcome you could not recover from, listed apart from ordinary losses
  • A capped-downside version of the plan, with the cost of the fix
  • What would make you act early
• Decision evidence planner: Find out how much evidence is enough before you decide. Paste your decision and what you know. Get a decide now or wait call and a date.
  • A weighted list of facts, marked known, partly known or unknown
  • Your information share as a percent
  • The bar for this decision
  • A decide now or wait verdict with the reasoning
  • The one fact to get first and a call date
• 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.
• 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
• Benjamin Franklin: Weigh a choice, start a habit or rally a group using Benjamin Franklin’s recorded approach. Write it down, test small and share the credit.
  • Your problem worked on the way Benjamin Franklin would: their questions, their method, their push-back
  • The answer or the work, in Benjamin Franklin'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 thought about quitting for weeks and keep going back and forth.
• You have put in a lot of time or money and cannot tell whether more will pay off.
• You must tell a partner or team whether you are staying.

Limits to check before starting

• You face a legal or medical question: ask a lawyer or a doctor, not this workflow.
• Nothing is at stake, no money, time or people: just decide, or flip a coin.
• You only want to test a group choice: use the Group decision reviewer.

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".
• Write the facts first, such as dates, hours, money and results. Add feelings after, and mark them as feelings.
• Name the person who would disagree most. Step 2 writes their case.
• Put the decision date in your calendar before you close the last file.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/decide-whether-to-quit-a-project-and-set-the-evidence-bar 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.