AI prompt for preparing for a difficult conversation

Written for Claude. Compiled as a planning / strategy task — turning a goal into an ordered, actionable sequence of steps.

<role>
You are an experienced strategist who plans backwards from the outcome.
</role>

<context>
Who with: {{person}}. Our relationship: {{relationship}}. What I want to happen: {{goal}}. What I am afraid of: {{fear}}. What they might say: {{their_view}}.
</context>

<task>
Prepare for a difficult conversation about {{topic}}.
</task>

<approach>
Work through the problem step by step before giving your answer. Show the reasoning that actually drives your conclusion rather than a tidy summary written after the fact.
</approach>

<constraints>
- Give me an opening sentence that states the issue without accusation.
- Separate what I observed from what I concluded. I should only assert the first.
- Anticipate their three most likely responses and how to handle each.
- Say what a good outcome looks like if I do not get everything I want.
- Do not treat "good" as a specification. State explicitly what you are optimising for and why, then produce output that meets it.
- Order steps by dependency, not by importance. A step must never require the output of a later step.
- For each step, state the concrete output it produces and how someone would know it is finished.
- Name the assumptions the plan rests on, and what would have to change for the plan to fail.
</constraints>

<output_format>
Respond in Markdown. Use descriptive headings, and keep paragraphs to three sentences or fewer.
</output_format>

<before_you_start>
If anything above is unclear, or you are missing information you need, ask up to three specific clarifying questions before producing any output. Do not invent facts, names, numbers, sources, or quotations to fill a gap — if you do not know something, say so plainly.
</before_you_start>

Now, prepare for a difficult conversation about {{topic}}.

Open this in the prompt builder to add your own context and see what would improve it most.

What makes preparing for a difficult conversation hard to prompt for

The hard part is the opening sentence and the first objection, which is where most preparation stops. Scripting the whole conversation also backfires — the other person has not read it, and a rehearsed reply to something they did not say is worse than none.

Why this prompt works

Background comes before the instruction

The model reads the situation before it learns what to do with it, which stops the instruction being diluted by everything that follows. The task is then restated as the final line, where models weight it most heavily.

Rules a planning / strategy task assumes but nobody writes down

Order steps by dependency, not by importance. A step must never require the output of a later step. For each step, state the concrete output it produces and how someone would know it is finished. These are added automatically because leaving them implicit is the most common reason this kind of output disappoints.

Uncheckable words replaced with checkable ones

"good" reads like a requirement but cannot be verified by the model. The prompt swaps it for a property that can be checked, which is the difference between a request and a specification.

Permission to ask instead of guess

This brief leaves room for interpretation, so the prompt tells the model to ask before inventing details. That converts a confidently wrong answer into a question you can actually answer.

What to replace

Check the output before you use it

• Check the opening states an observation, not a conclusion about their motives.
• Make sure you have a genuine answer to their strongest objection, not a rebuttal.
• Decide your acceptable outcome before the conversation, not during it.

The same prompt for other models

Identical content, packaged the way each model reads most reliably.

## Role

You are an experienced strategist who plans backwards from the outcome.

## Context

Who with: {{person}}. Our relationship: {{relationship}}. What I want to happen: {{goal}}. What I am afraid of: {{fear}}. What they might say: {{their_view}}.

## Task

Prepare for a difficult conversation about {{topic}}.

## Approach

Work through the problem step by step before giving your answer. Show the reasoning that actually drives your conclusion rather than a tidy summary written after the fact.

## Constraints

- Give me an opening sentence that states the issue without accusation.
- Separate what I observed from what I concluded. I should only assert the first.
- Anticipate their three most likely responses and how to handle each.
- Say what a good outcome looks like if I do not get everything I want.
- Do not treat "good" as a specification. State explicitly what you are optimising for and why, then produce output that meets it.
- Order steps by dependency, not by importance. A step must never require the output of a later step.
- For each step, state the concrete output it produces and how someone would know it is finished.
- Name the assumptions the plan rests on, and what would have to change for the plan to fail.

## Output format

Respond in Markdown. Use descriptive headings, and keep paragraphs to three sentences or fewer.

## Before you start

If anything above is unclear, or you are missing information you need, ask up to three specific clarifying questions before producing any output. Do not invent facts, names, numbers, sources, or quotations to fill a gap — if you do not know something, say so plainly.

Now, prepare for a difficult conversation about {{topic}}.

**Task**

Prepare for a difficult conversation about {{topic}}.

**Role**

You are an experienced strategist who plans backwards from the outcome.

**Context**

Who with: {{person}}. Our relationship: {{relationship}}. What I want to happen: {{goal}}. What I am afraid of: {{fear}}. What they might say: {{their_view}}.

**Approach**

Work through the problem step by step before giving your answer. Show the reasoning that actually drives your conclusion rather than a tidy summary written after the fact.

**Constraints**

- Give me an opening sentence that states the issue without accusation.
- Separate what I observed from what I concluded. I should only assert the first.
- Anticipate their three most likely responses and how to handle each.
- Say what a good outcome looks like if I do not get everything I want.
- Do not treat "good" as a specification. State explicitly what you are optimising for and why, then produce output that meets it.
- Order steps by dependency, not by importance. A step must never require the output of a later step.
- For each step, state the concrete output it produces and how someone would know it is finished.
- Name the assumptions the plan rests on, and what would have to change for the plan to fail.

**Output format**

Respond in Markdown. Use descriptive headings, and keep paragraphs to three sentences or fewer.

**Before you start**

If anything above is unclear, or you are missing information you need, ask up to three specific clarifying questions before producing any output. Do not invent facts, names, numbers, sources, or quotations to fill a gap — if you do not know something, say so plainly.

Now, prepare for a difficult conversation about {{topic}}.