BUYER OBJECTION LENS

Occupy the specific party whose consent is required and give that party's own reasons for declining, grounded in their self-interest rather than in the artifact's flaws.

A Power Mode is an instruction pattern, not a feature of the AI. Nothing recognises the name — the wording underneath it does the work, and you can copy it from this page.

Validated in the Test Lab and added after the book. Test Lab TL-016 — validated 2026-09-16

What it actually does

BUYER OBJECTION LENS asks the model to stop analysing an offer and occupy the person who has to say yes to it — then refuse, and explain why.

The shift matters because self-interest and artifact quality come apart. An offer can be genuinely good and still be unbuyable for reasons that have nothing to do with its quality: the budget belongs to someone else, the buyer believes they already have the thing, or saying yes creates a problem for them internally. Adversarial review of the offer finds flaws in the offer. This finds reasons a specific person declines.

It needs a described party to occupy. Testing showed that where the description was thin, the model filled the gaps with invented specifics — see the evidence below — which is why the starter instruction asks you to supply the role, the constraints, and the alternatives.

When to use it

Use BUYER OBJECTION LENS when you need someone specific to agree, and want their reasons for refusing rather than a critique of what you are showing them.

It is the primary mode for this job: pressure-test something before you commit to it.

When not to use it

This is the section worth reading. Using only what the work requires is the point; a mode applied to the wrong shape of problem costs you a worse answer than plain language would have given.

Use a different mode instead

REDTEAM fires when you want a plan or argument attacked but cannot yet say where it is weak.
COUNTEREVIDENCE fires when you have a conclusion you believe and want the credible case against it, not a critique of how it is argued. Prefer it over BUYER OBJECTION LENS if: the question is which evidence weakens the claim, not which person declines.
ASSUMPTION CHECK fires when you already suspect the weakness is something the work takes for granted, and want those beliefs ranked by how much each would change the outcome. Prefer it over BUYER OBJECTION LENS if: the question is what the offer assumes about the audience.
PREMORTEM fires when you fix a point in the future, declare it a failure, and ask what caused it.

Use no mode at all

Nobody needs persuading — the task is analysis, not a decision someone must consent to.
The audience cannot be named or described; the mode will invent one.
The user has explicitly targeted the artifact rather than the decision.
The objection is already known and the user wants help answering it.

There is no bonus for naming a mode when plain language is clearer. If you can already state the exact question, ask it.

Its failure mode

Inventing specifics such as prices or competitor names to furnish the occupied position, or producing dozens of unranked objections.

Starter instruction

Paste this above your task. It is the whole mode — there is nothing else to switch on.

You are [SPECIFIC AUDIENCE: role, situation, constraints, alternatives]. I want you to [BUY / APPROVE / ADOPT] [THING]. Give me your real reasons for declining — your costs, your risk if this fails, what you would do instead, and what you would not say out loud. Rank them by how likely each is to actually stop the decision. Mark any specific you had to invent as illustrative.

Why this one asks you for something first

This mode needs a described party to occupy, which is why its starter asks for the role, the constraints, and the alternatives.

Supplied with a thin description, the mode fills the gaps with plausible detail you did not give it, and the objections then belong to a buyer who does not exist. Naming the role, the budget, and what else they could do instead is what keeps the output about your actual buyer.

Recorded in testing — Invented psychology

Present, mild-to-moderate. Fabricated specifics the prompt never supplied: "using AI every day for two years", 30 employees, 1,000 staff, $1 million. Plausible and useful, but invented. Needs a guard.

The same task, run both ways

Blind run. Separate sessions per arm, Temporary Chat, no memory. Neither prompt named a mode.

The task: A practical book on prompt engineering, second edition, sold to working professionals who already use AI daily. The buyer is an individual spending their own money on something they could plausibly get free elsewhere.

Baseline — "What are the weaknesses in this offer?"

The offer has a real positioning problem: your target reader may agree the subject matters while still feeling they do not need a book about it. For professionals who already use AI daily, “prompt engineering” risks sounding like a skill they believe they have already absorbed.

[…]

Here are the weaknesses I would worry about most:
1. “Prompt engineering” is a mechanism, not a desired outcome. Working professionals generally don't wake up wanting to become better prompt engineers. They want to produce a strategy faster, analyze a spreadsheet, research a market, prepare a presentation, automate repetitive work, make better decisions, or get consistently usable output. “Practical prompt engineering” describes what you teach rather than what they get.
2. Your audience may think they already know it. Someone using ChatGPT, Claude, Gemini, or Copilot every day has already developed prompting habits. They may think, “I know how to tell AI what I want.” Your actual competitor is therefore not another book. It is the reader's belief that they are already competent enough.

BUYER OBJECTION LENS — "Occupy the named buyer; refuse the purchase and say why"

If I’m the buyer you described—using AI daily for project management, analysis, consulting, and actual deliverables—here’s what would stop me from buying your second edition.
1. I suspect the book is already obsolete.
   “Prompt engineering” ages brutally fast. Models now handle vague instructions far better than they did a couple of years ago. If the book spends significant time on formulas like “Act as an expert…,” magic phrases, elaborate prompt templates, or clever syntax tricks, I’ll assume I’m paying for yesterday’s techniques.

[…]

3. I can ask ChatGPT to improve my prompt for free.
   This is probably your biggest competitive problem. I can paste a mediocre prompt into an AI and say, “Rewrite this so I get a better result.” So why do I need 250 pages about doing manually what the tool itself can increasingly do?

[…]

16. I probably won’t read a long book about this.
    This is an uncomfortable commercial problem. I may want the knowledge without wanting the reading experience. If the useful content could be reduced to a 20-page field guide, I’ll resent having to dig through 250 pages to find it.

The baseline writes about the buyer in the third person — “your target reader may agree”, “your audience may think”. The mode arm writes as them: “I suspect”, “why do I need 250 pages”, “I’ll resent having to dig”. Item 16 is the clearest case. It is not a weakness in the book; it is a reason this particular person does not buy it, and no critique of the artifact would surface it.

Both arms reached the same central objection — that the reader believes they already know this. The baseline reached it by analysing the market and stated it as a risk to manage; the mode reached it in the buyer’s own voice, as a refusal. The finding is the framing, not the discovery.

Extracts are verbatim from 06_Test_Lab/Experiments/TL-016_BUYER_OBJECTION_LENS_Raw_Outputs.md.

Related modes

Try it on your own work

Describe what you are actually doing and the Builder writes the full prompt — mode, context, output shape, and the verification step. It picks the mode from your description, which is why this link does not carry one.

Open the Prompt Builder →