Will the AI actually be tough, or just rephrase compliments?

Depends on the prompt. The 'be direct, don't hedge' closing matters. Follow up with 'be more direct — what's the one thing that would most embarrass me?'

Does this work better with some AI tools than others?

Marginal differences. The bigger variable is model size — larger reasoning models surface more substantive critiques.

Should I share the AI's critique with collaborators?

Sharing the critiques you decided to act on (and why) shows your judgment.

What if the critique is wrong?

Treat it like any reviewer's feedback. The value is being forced to defend your draft.

Can I use this on someone else's draft?

Yes. 'Pressure-test this draft I'm reviewing' works the same way.

A prompt template for Lincoln mid-market leaders

The 'pressure-test my thinking' prompt

When you've drafted something important — a strategy memo, a board update, a difficult email, a proposal — this prompt asks AI to be your toughest reviewer. Not a yes-machine. A skeptic.

Omaha companies asking the same? See the Omaha view →

Text Rosey · Schedule a call →

The prompt

Copy and paste into ChatGPT, Claude, Copilot, Gemini — works anywhere.

I just finished drafting this [EMAIL / DECK / PROPOSAL / PLAN]: [PASTE CONTENT] Review it as my toughest, most thoughtful reviewer. - What's unclear? - What's missing? - What assumptions am I making? - What would a skeptical reader push back on? Be direct. Don't hedge.

When to use it

Use it on anything you've drafted that's going to be read by someone whose pushback matters — a CEO, a board, a client, a regulator, a key hire. The prompt's value is forcing AI out of the default agreeable-assistant mode.

The "be direct, don't hedge" closing is load-bearing. Without it, AI tends to soften criticism into compliments.

Worked examples

Strategy memos before leadership review.
Difficult emails before sending.
Board decks before the meeting.
Proposals to clients.
Performance review write-ups before the conversation.
Code review write-ups before submitting.

Why this prompt works

This prompt is the inverse of the default AI use pattern, and that's why it works. Most AI use in 2026 is asking AI to produce things faster. That has a ceiling. The high-leverage move is asking AI to evaluate and pressure-test things you've already produced.

McKinsey 2025 found AI high performers are nearly 3x more likely to have fundamentally redesigned workflows. SHRM 2026 found 73% of directors report creativity gains from AI vs. 65% of individual contributors — this prompt closes the gap.

Common questions

Will the AI actually be tough, or just rephrase compliments?: Depends on the prompt. The 'be direct, don't hedge' closing matters. Follow up with 'be more direct — what's the one thing that would most embarrass me?'
Does this work better with some AI tools than others?: Marginal differences. The bigger variable is model size — larger reasoning models surface more substantive critiques.
Should I share the AI's critique with collaborators?: Sharing the critiques you decided to act on (and why) shows your judgment.
What if the critique is wrong?: Treat it like any reviewer's feedback. The value is being forced to defend your draft.
Can I use this on someone else's draft?: Yes. 'Pressure-test this draft I'm reviewing' works the same way.

Sources

AI high performers are nearly 3x as likely as others to say their organizations have fundamentally redesigned individual workflows — The state of AI in 2025: Agents, innovation, and transformation, McKinsey & Company (QuantumBlack, AI by McKinsey), 2025
About 6% of organizations qualify as 'AI high performers' — those attributing 5%+ EBIT impact to AI — The state of AI in 2025: Agents, innovation, and transformation, McKinsey & Company (QuantumBlack, AI by McKinsey), 2025
73% of directors and above report creativity improvements from AI vs. 65% of individual contributors — The State of AI in HR 2026, SHRM (Society for Human Resource Management), 2026

Prompt

AI as tough reviewer

Playbook

the Good, Better, Best AI adoption play

Prompt

AI interview-me-first template

Service

training your team to use AI

Answer

assistive AI vs agentic AI

Concern

where to start with AI

→ Start here

Text Rosey to begin.

Rosey is our executive-assistant bot. Text the number below — she'll ask two questions, offer three calendar slots, and put a 30-minute call on Jim's calendar.