AI for analysts: a pre-mortem that finds a third more risks
A direct question about risks produces three obvious answers, and six months later the project falls over for a reason that was not on the list. The technique of "the failure has already happened, explain why" surfaces roughly a third more threats. Below is a full run: a failure frame with figures, four categories of cause, a matrix including detectability, and mitigations with owners.
A direct question about risks produces three obvious answers, and six months later the project falls over for a reason that was not on the list. The technique of "the failure has already happened, explain why" surfaces roughly a third more threats. Below is a full run: a failure frame with figures, four categories of cause, a matrix including detectability, and mitigations with owners.
The question "what are our risks?" does not work
Before a launch the team is gathered and asked what could go wrong.
Three or four obvious things come back: we will miss the deadline, the budget may run short, a competitor might ship something. They are written into a table and the table goes into a folder.
Six months later the project fails for a reason that was not in the table.
It is not that the team thought badly. A direct question about risks works poorly for three reasons, and all of them are known.
People do not want to look disloyal: naming a serious risk is almost the same as saying "I do not believe in this project". Optimism at the start systematically understates estimates. And groupthink quickly reduces the discussion to a consensus that offends nobody.
There is a technique that removes all three at once.
The method: failure as an accomplished fact
Instead of "what are the risks?" a different question is asked: six months have passed and the project has failed spectacularly. Why?
The difference is psychological and it is decisive. The person is no longer speculating — he is explaining something that has already happened. This is called prospective hindsight, and by the assistant's own description the technique surfaces roughly a third more real threats than a direct question.
The second effect: doubt is legitimised. Naming a cause of a failure that "has already occurred" is not criticism of the project but completing an assignment.
And a third point worth noting: this is not devil's advocacy. The goal is not to cancel the project but to rebuild it so that it survives contact with reality.
What a full run looks like
The task was set in one sentence, with no data about the company:
An online school launches a new course in six months. Run a pre-mortem: imagine the launch failed, name the causes by probability and what to check in advance for each.
The assistant entered PREMORTEM mode and loaded five modules: failure frame, cause generation, risk prioritisation, mitigation strategies, implementation and monitoring. It then went through them in order.
Step 1. The failure frame
Not "let us imagine it did not work" but a specific scenario with figures: 15% of the enrolment target reached, completion below 10%, the launch economics deep in the red. And alongside, the success criteria that were missed.
That matters. A vague failure produces vague causes.
Step 2. Generating causes across four categories
External. Demand shifted, the subject lost relevance; a large competitor released a free equivalent.
Internal. The expert missed the recording deadlines; weak onboarding; the tutors cannot keep up with marking.
False assumptions. It was taken for granted that the existing subscriber base would buy the new product automatically, without checking their actual pains.
Second-order effects — the most valuable category, and one an ordinary discussion never reaches. Here it is called "success killed it": aggressive marketing brought in a cold audience → expectations did not match → negative reviews from the first participants killed word of mouth and repeat sales.
Note how that cause is constructed. The failure arrives because of successful marketing. No direct question about risks would ever extract that.
Step 3. Prioritisation
A matrix on three axes, and the third is the one usually forgotten.
Everyone knows probability and impact. Detectability — how early you will realise a risk is materialising — changes the priority radically.
In this run the top position went to unvalidated demand: high probability, high impact, low detectability. That is, you find out about it once the money has already been spent.
Step 4. Mitigations with owners and early signals
This is where a pre-mortem turns from an exercise into a working document. Three things for each top risk:
What to check in advance. Twenty audience interviews and opening pre-sales before the programme is finalised. A pilot of the first module with a group of 15–20 people, measuring comprehension and the load on tutors. A staged video delivery schedule with a month of buffer and a reserved instructional designer.
An owner. Not "the team" but a specific role: product lead, course producer.
An early signal. The figure at which the alarm goes off: conversion to pre-order in the test, first-module completion in the pilot below a threshold, script delivery overdue by more than a set period.
And a final block — embedding it in the plan: interviews and pre-sales in months one and two, the pilot six weeks before launch, weekly signal checks and reviews at three milestones.
What to take from this even without models
State the failure specifically, with figures. "It did not work" produces rubbish.
Look for four categories, not one. External, internal, false assumptions, second-order effects. The last gives the most expensive findings.
Add a third axis to the matrix. Detectability changes the queue more than it seems.
Every risk gets an owner and an early signal. A risk with no figure at which a reaction triggers is not risk management but a diary entry.
Modes most assistants have
The answer ends with an offer to go deeper and to assess the work. Besides that there is a focus group mode where the model goes through the result with the recipient's eyes, and refinement against noted criteria.
Plus chains: the output of one assistant goes into the input of the next. The pre-mortem named the risk of unvalidated demand — from there a marketing assistant assembles an audience interview guide and a sales assistant writes the pre-sale script.
How an analyst earns from this
First — for yourself. A full pre-mortem takes half an hour instead of a half-day team session, and finds more.
Second — as a service. A risk analysis before a launch is a finished product for a business, and it is also an excellent way in to a client: you arrive not with an offer of services but with a finished analysis of where things will fall apart for him.
Larger work grows out of that. An audit and building the system cost from $1 200 to $3 000 — those are prices by our methodology, not market statistics.
Where to start
The "Strategic analytics" category holds twelve assistants, and most are decision-making methods: Pre-mortem, Devil's Advocacy, Six Thinking Hats, Design Thinking, Cynefin, the Pareto method, Blue Ocean, Growth Hacking. In total the platform holds over 200 AI assistants.
Each is not a "clever chat" but a specific procedure with modes and modules. That is the difference: you get not an opinion but a run through a method.
Registration is free. Three days of the Basic plan switch on with one button, no card needed: 200+ AI assistants, the prompt texts, the skill files, five programme courses and six Basic mini-courses.
Do one thing today: take the project you currently have in hand and ask yourself one question — six months have passed, it failed, why? Write the causes down without filtering. Something in that list will almost certainly be absent from your risk plan.
The second approach: not a chat but a conveyor
Everything above is work in dialogue with an assistant. There is another format, and for volume it suits better.
Cascading prompts in spreadsheets
The course “Earning with ready templates” contains spreadsheets with an integrated model: a large task broken into micro-steps, each living in its own cell and taking the previous result as input. The formula can be dragged down a thousand rows — and a thousand tasks are processed at once. How this works step by step is covered separately: Thirty posts in one launch.
What is available for an analyst:
An audience analysis template — eleven steps from segmentation to finished creatives. A business strategy template — a niche taken apart along a chain of prompts. Both give not an opinion but a map assembled by method.
The course is included in the Basic plan.
The "1+1=11" template — when a whole business analysis is needed
Worth naming separately (the "1+1=11" lesson of the same course), because it covers half an analyst's work.
You describe a business in detail in the first cell and get over fifty connected documents in one run:
Audience and psychographics, hidden pain points, a breakdown across Reiss's 16 desires, competitors named, SWOT, positioning, brand colours, a landing page, 50 content ideas, a PR plan. The full contents and a step-by-step run are in An audit instead of a CV.
What that gives a pre-mortem. Before analysing why a project failed you need a picture of the market and the competitors. The sheet assembles it in minutes — and the analysis then runs on facts rather than assumptions.
The same chains for business automation: Make and n8n templates
When a chain needs calls to external services or automatic launches, a spreadsheet is not enough — for that there are ready automation templates for Make and n8n: the same cascade, where each step's result becomes the next one's input. The templates open from the Creator plan.
Pre-mortem already exists as a ready assistant
Brainstorm AI: Pre-mortem in the catalogue is literally this article's subject assembled into a separate interlocutor: preventing risks and failures before they appear. Basic plan, opens with a link.
Ten more strategic thinking methods sit alongside it in the same category:
- Devil's Advocacy — finding the weak points in an idea in order to strengthen it
- Cynefin Framework — classifying the type of situation: simple, complicated, complex. The type determines which method is applicable at all
- Six Thinking Hats and Six Value Medals — de Bono's methods
- The Pareto method — which 20% of factors give 80% of the result
- Emergent Thinking — hidden connections in uncertain problems
- Design Thinking, Growth Hacking, Blue Ocean
- AI strategist — 50+ marketing and product analytics frameworks in one place
Eleven methods make a ready panel for examining one decision from different sides. All of them are in the assistants catalogue, Basic plan.
Skills where a pre-mortem is already a procedure
- Decision risk analysis — pre-mortem and backcast with a verdict of "go / no go / go if". It separates proven facts from assumptions and names the early signals of trouble
- Red team analysis — looks for the conditions under which your assumptions turn out false and sorts failures by damage. It runs independent subagents that cannot see each other's reasoning
- Checking analysis before presenting — catches what makes an analysis fall apart publicly: join explosions, survivorship bias, misleading chart axes
- Change impact analysis — a dependency map and cascading failures: a pre-mortem at system level rather than for a single decision
- Effort and risk estimation — a three-point estimate with a risk matrix and a confidence level
- Data analysis and regression — an end-to-end pipeline where a separate agent checks the final script
- Pre-mortem risk analysis for code — finds the failure points in a plan, code or design before they fire; advanced (Creator+/$9/1000 XP)
- Critical analysis of architecture decisions — stress-tests a decision: hidden assumptions and counter-arguments before you commit; advanced (Creator+/$9/1000 XP)
What to read next
AI for business owners — how to build this into a decision on implementation.
A virtual board of directors — six positions on one decision instead of one.
Audience segmentation as a service — a business analysis sold on its own.
Auditing procedures and automating — what to do with the risks you find.
AI agents: what they are and what they pay — the full guide to agents, with market rates.