Complete AI Training
Sign inGet started

AI agent for chief executing officers

Executive Decision Pre-mortem Agent

Surface and address the likely failure causes before a decision is made.

Risk managementManagementExecutives and strategy
See how it worksGet access
Executive Decision Pre-mortem Agent: what goes in, what the agent does and what you get

What it does

Big decisions are reviewed for benefits, and the risks get a short slide. When the project fails, everyone says they saw it coming. A pre-mortem asks in advance: imagine this failed, why? This agent reads the proposal and lists the ways it could fail. It checks each against data and past projects, such as similar acquisitions that missed their synergies. It asks owners for mitigations, then rechecks that each serious cause has an owner and a date, and that the mitigation is stronger than what failed before. Causes without a real answer go back to their owners. The executive approves the final list. Edge case: a failure cause that appears in two past projects is shown first with the earlier outcome.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueYes, continueApprovedNoNo 1 STARTS WHEN A proposal is submitted for decision 2 USES A TOOL Read the proposal and its assumptions 3 DOES List ways it could fail by area 4 USES A TOOL Check each against data and similar past projects 5 DOES Rank causes by likelihood and impact 6 USES A TOOL Ask owners for mitigations 7 CHECKS THE RESULT Does each high-ranked cause have a named mitigationand owner? If not: Return the open causes to the owners with adeadline. Back to step 6. 8 CHECKS THE RESULT Do the mitigations match the evidence from pastprojects? If not: Mark them weak and ask for stronger actions.Back to step 4. 9 YOU APPROVE Executive approves the final list 10 RESULT Pre-mortem register
Read the steps as a list
  1. A proposal is submitted for decision
  2. Read the proposal and its assumptions
  3. List ways it could fail by area
  4. Check each against data and similar past projects
  5. Rank causes by likelihood and impact
  6. Ask owners for mitigations
  7. Does each high-ranked cause have a named mitigation and owner?If not: Return the open causes to the owners with a deadline. Back to step 6.
  8. Do the mitigations match the evidence from past projects?If not: Mark them weak and ask for stronger actions. Back to step 4.
  9. Executive approves the final listThe agent waits here for your OK.
  10. Pre-mortem register

How it decides

Ranks failure causes by likelihood from past cases and by impact on the goal, and counts a cause as handled only with a named mitigation and owner.

  • Cause in two or more past projects is ranked first
  • High impact and high likelihood needs a mitigation
  • Mitigation needs an owner and a date
  • Unmitigated causes are shown in the decision paper

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Areas to review
  • Past projects to compare
  • Risk ranking method
  • Deadline for owner replies (default 5 days)
  • Decision papers to attach

What keeps you in control

It always asks you first

  • The final list
  • Any change to the proposal
  • Any decision to proceed

Hard limits

  • Never decide or approve the proposal
  • Never hide a high risk

It stops when

  • Done: all high risks have mitigations
  • Stop: proposal withdrawn
  • Stop: decision made without review

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensA proposal to acquire a supplier lists synergies of 8 million. The agent finds two past acquisitions missed integration targets by 40% due to system differences. It ranks that cause first. The owners offer an integration lead but no date. The check fails, so the agent asks again. A date and a pilot are added. The executive approves the register.

More agents for chief executing officers

Risk management · Analysis

Supplier Concentration Risk Agent

A map of single-source risk with the largest exposures reduced.

10 steps1 check9 jobs Quality control · Analysis

Executive Dashboard Anomaly Check Agent

Only real changes in the numbers reach the leadership meeting.

10 steps1 check8 jobs Quality control · Analysis

Sustainability Initiative Impact Tracker Agent

Sustainability claims that match tracked data, with gaps listed.

10 steps2 checks8 jobs Document handling · Administration

Leadership Meeting Prep and Decision Log Agent

Hold every leadership meeting with complete, checked papers and a decision log that closes.

11 steps2 checks11 jobs