What If AI Were Forbidden to Give Answers?
What if the greatest potential of Generative AI is not generating answers, but generating possibilities?
We are living in an extraordinary age.
Ask AI to write an email, and it produces one. Ask it to summarize a report, and it responds in seconds. Ask it to recommend a strategy, and it offers a structured plan.
The better AI becomes at answering, the more we rely on it.
But consider a strange possibility:
What if AI were forbidden to give answers?
Would it become useless?
Or would we discover an entirely different kind of intelligence partnership?
Welcome to PO Prompts #003, where we use Edward de Bono's provocative thinking approach to explore what AI could become when we stop treating it merely as an answer machine.
1. The Story: The Professional Who Had All the Answers
Arjun is a young professional working in a technology company.
His day begins with AI.
He uses it to draft emails, summarize meetings, prepare presentations, analyze documents and recommend solutions.
His productivity has improved dramatically.
One afternoon, during a strategy meeting, his manager asks a simple question:
“What possibilities have we not considered?”
Arjun opens his AI assistant.
Within seconds, he receives ten recommendations.
They are sensible, well-structured and professionally presented.
But something bothers him.
Most of the suggestions are variations of ideas the team has already discussed.
The manager asks another question:
“What if our entire approach to this problem is wrong?”
Arjun hesitates.
For the first time, he realizes that having more answers does not necessarily mean discovering more possibilities.
Perhaps he has been asking AI the wrong kind of questions.
2. The Hidden Assumption
Most interactions with AI follow a familiar pattern:
Human asks → AI answers → Human acts.
Behind this pattern lies an assumption:
The primary value of AI is its ability to provide useful answers.
This assumption is understandable. Answer generation is one of AI's most visible capabilities.
But it is not the only way AI can contribute to thinking.
AI can also help us explore alternatives, construct hypothetical scenarios, examine assumptions and develop ideas that would otherwise remain unexplored.
What happens when we deliberately remove the expectation of an immediate answer?
3. Enter PO: What If AI Were Forbidden to Give Answers?
Edward de Bono introduced PO as a tool for provocative thinking.
Unlike an ordinary question, a PO statement can deliberately introduce an unreasonable or impossible condition to disrupt habitual thinking.
The purpose is not to prove the statement correct.
It is to use the provocation as a stepping stone toward new ideas.
Our provocation is:
PO: AI is forbidden to give answers.
Imagine that tomorrow, every AI assistant receives a new instruction:
You may not provide direct answers or recommendations.
Instead, AI must help users explore what they have not yet considered.
What could such an AI do?
It might challenge assumptions rather than accept them.
It might ask questions that expose overlooked possibilities.
It might introduce deliberately unusual perspectives.
It might help people imagine alternative futures.
And it might turn surprising ideas into experiments.
The apparent restriction could reveal an entirely different source of value.
AI becomes a possibility engine rather than only an answer engine.
4. PO Thinking Lab — From Answers to Possibilities
This is where the reader becomes an active participant.
The goal is not merely to appreciate the provocation. It is to use it.
Step 1 — Recognize the conventional thinking
Consider a problem you are currently facing.
Perhaps you are planning a project, making a career decision, improving a business process or designing a new product.
Your usual AI prompt might be:
“What is the best solution to this problem?”
Notice what this question assumes.
It assumes that the problem is already correctly defined and that the next step is to identify a solution.
But what if the problem itself needs to be questioned?
Step 2 — Challenge the assumption
Ask yourself:
What am I taking for granted?
Why do I believe this is the problem?
Which alternatives have I already excluded?
What would someone from an entirely different field notice?
The objective is not to reject established knowledge. It is to expose assumptions that may be unnecessarily limiting our thinking.
Step 3 — Introduce the PO provocation
Now impose the unusual rule:
PO: AI cannot give me an answer.
It can only help me discover possibilities.
Instead of asking, “What should I do?”, ask:
“What possibilities am I failing to see?”
This changes the direction of the conversation.
Step 4 — Move through five possibilities
Consider five potential roles for an answer-free AI.
Possibility A — The Assumption Challenger
AI identifies assumptions embedded in the user's problem and explores what might happen if they were removed.
Possibility B — The Question Inventor
Instead of producing solutions, AI generates unfamiliar, provocative questions that open new directions.
Possibility C — The Alternative-Future Explorer
AI helps users imagine different scenarios, including ones that seem improbable today.
Possibility D — The Perspective Shifter
AI examines a problem from the viewpoints of customers, competitors, beginners, future generations or entirely different professions.
Possibility E — The Experiment Designer
AI helps transform unconventional possibilities into small, testable experiments without prematurely claiming that an idea will work.
These are not predictions about what every AI system should become.
They are possibilities revealed by the provocation.
Step 5 — Discover the movement
We began with a seemingly absurd restriction:
AI is forbidden to give answers.
But the restriction reveals an important distinction.
Answer generation helps us work within a problem frame.
Possibility exploration helps us reconsider the frame itself.
Both are valuable.
The breakthrough is recognizing when each is needed.
Step 6 — Run a real experiment
Choose one decision you are facing this week.
For your first AI conversation about it, prohibit immediate recommendations.
Ask AI to identify assumptions, generate five distinct ways of framing the issue and explore their implications.
Then select one surprising but plausible direction.
Only after this exploration should you ask AI to help evaluate and implement it.
Compare the experience with your usual answer-seeking approach.
Did you discover a possibility you would otherwise have missed?
5. The Complete ChatGPT PO Prompt
Copy this prompt into ChatGPT and try it with a real problem.
Act as my PO lateral-thinking partner, inspired by Edward de Bono's concept of provocation.
For this conversation, do not begin by giving me answers or recommendations.
Instead:
Help me identify the hidden assumptions behind my problem.
Introduce one deliberately provocative PO statement that challenges those assumptions.
Explore at least five distinct possibilities that emerge from the provocation.
Help me move from unusual ideas toward potentially useful concepts.
Challenge me with questions that expand my thinking.
Help me select one possibility for a small, practical experiment.
Distinguish speculative possibilities from established facts. Do not evaluate ideas too early.
Begin by asking: “What problem, decision, or opportunity would you like to explore differently?”
The purpose of this prompt is not to eliminate answers forever.
It is to create space for exploration before committing to an answer.
6. PO and Generative AI: A Powerful Partnership
Generative AI can produce many ideas, scenarios and variations.
But generating more content does not automatically produce genuinely new thinking.
If our prompts remain trapped within familiar assumptions, AI may simply generate more sophisticated variations of familiar solutions.
This is where PO becomes especially relevant.
PO disrupts the direction of thinking.
AI expands the possibilities that emerge.
Human judgment evaluates their usefulness.
Experimentation turns promising possibilities into accomplishments.
We can express this partnership as:
PROVOKE → GENERATE → MOVE → ACCOMPLISH
This is not a claim that every provocative idea is valuable or that AI-generated possibilities are automatically correct.
It is a practical approach for combining creative exploration with responsible judgment.
And it connects directly to the philosophy of AIYING — Accomplishing with AI.
7. The Bigger Insight
We often ask:
How can AI help me do this better?
PO invites a different question:
What if I should be doing something entirely different?
That is a fundamental shift.
The first question improves an existing direction.
The second opens the possibility of discovering a new one.
The most valuable AI conversations may involve both.
First, expand what is possible.
Then, determine what is useful, responsible and achievable.
8. Your PO Challenge
For your next important decision, try this:
Spend five minutes with AI without asking for a single solution.
Ask only for assumptions, provocations, alternative perspectives and unexplored possibilities.
Then reflect:
Did AI give you something more valuable than an answer — a new direction?
Share the most surprising possibility you discovered.
PO Prompts — One Strange Question. A New Possibility.
One Image. One Story. One Provocation. Many Possibilities.
AIYING — Accomplishing with AI.
