⚡ Promptolis Original · Relationships & Life
📝 Hard Conversation Preparation Workbook
30-60 min structured prep before the hard conversation you've been avoiding.
Hard Conversation Preparation Workbook — 30-60 min structured prep before the hard conversation you've been avoiding. Setup: 2 min to try · Best AI: Opus 4 for nuance. · Cost: Free, MIT-licensed.
Why this is epic
Most difficult conversations go badly because of under-preparation. Harvard Negotiation Project's research: 30-60 min structured prep dramatically improves outcomes. Not rehearsing lines — understanding stakes, feelings, what's genuinely being discussed.
Three-conversation framework (Stone/Patton/Heen): every hard conversation is actually three simultaneous conversations. What happened, Feelings, Identity (what this says about me). Naming which you're having clarifies.
📑 Page navigation + Key Takeaways Click to expand
📌 Key Takeaways
- What it is: 30-60 min structured prep before the hard conversation you've been avoiding.
- Best for: Before any hard conversation (work, family, romantic)
- Time investment: 2 min to try setup, 30-60 min preparation output
- Recommended AI model: Opus 4 for nuance.
- Cost: Free forever — MIT-licensed, no signup, no paywall
📑 On this page
- The prompt (copy-ready)
- How to use it (4 steps)
- Example input + output
- Common use cases
- Pro tips + variants
- FAQ
⚙️ At a glance
- Category:
- Relationships & Life
- Setup time:
- 2 min to try
- Output time:
- 30-60 min preparation
- Best AI model:
- Opus 4 for nuance.
- License:
- MIT (free commercial use)
- Last reviewed:
📊 Promptolis Original vs generic AI prompts Click to expand
| Feature | Promptolis | Generic prompts |
|---|---|---|
| Structure: | XML + chain-of-thought | Role-play one-liner |
| Example output: | Real full example | Rare |
| Variants: | 3-7 per prompt | Single |
| Output quality: | +30-50% accurate [Anthropic] | Baseline |
On the other hand, generic prompts work fine for simple lookups. Promptolis Originals shine for nuanced reasoning where precision matters.
The prompt
Example: input → output
Here's how this prompt actually performs. Real input below, real output from Claude Opus 4.
<conversation-topic>Mom's ongoing criticism of my parenting</conversation-topic> <relationship>Mother, 68, we're close but this has grown worse last year</relationship> <what-happened>Each visit, she makes comments about my kids' behavior, my discipline style, food choices. I nod, internalize, resent. Last visit she said 'when you were little I never let you speak to me that way' implying I'm too permissive.</what-happened> <avoidance-duration>18 months</avoidance-duration>
The Three Conversations Analysis
What happened: Specific pattern — mom's critical comments about parenting across visits. You nod + internalize + resent.
Feelings conversation (the real one): You feel judged, undermined in front of your kids, unseen for the work you're doing, grief for the mom-daughter relationship you wanted. She possibly feels protective/wise/rejected.
Identity conversation: Who are you as a mother? Her criticism implies 'bad mom.' Her criticism also says something about her — is she feeling obsolete/unneeded? Are you carrying her criticism as internal judge?
All three happening simultaneously. The What-Happened is the surface; Feelings + Identity are the content.
Your Intent Check
Honest: what do you want?
- Her to stop? (change her behavior)
- Her to understand? (change her understanding)
- Validation for yourself? (change what you feel)
- To preserve relationship while setting limit?
Probably: preserve relationship + set limit on criticism + want her to understand impact. That's fair goal.
Intent NOT to aim for: 'win' or 'make her feel bad.' Those destroy relationships.
Your Contribution Owned
Honest reflection:
- You've nodded for 18 months = tacit permission. She may genuinely think you're fine with it.
- Your silence on criticism isn't neutrality — it's a boundary not yet spoken.
- You may also want her approval in ways that feed the dynamic.
Bring: 'I haven't said anything about this for a long time. That's not fair to you — you can't know what I haven't said. I'm bringing it now.'
Specific Outcome You Want
Realistic ask:
- Not 'stop criticizing.' (Too vague, probably impossible.)
- Maybe: 'I need you to trust I'm making parenting decisions + hold critiques unless I ask for them.'
- Specific: 'When we visit, I'm asking that comments about discipline / food / behavior stay between us privately, not in front of the kids.'
Specific, behavioral, limited. Negotiable.
Opening 2-3 Sentences
'Mom, I love you and I want to talk about something that's been on my mind. I haven't brought it up because I worry it'll hurt you, and my avoidance hasn't been fair to you. Can I share honestly?'
Wait for yes.
Then: 'The way you comment about my parenting during visits — I've been nodding but internally it's been painful. I think it's because [your truth]. I want to understand your perspective, and I want to ask for something specific going forward.'
What To NOT Say
- 'You're always criticizing me.' (Over-generalization; puts her on defense.)
- 'You messed up parenting too.' (Counter-attack; destroys conversation.)
- 'Just stop.' (Boundary without explanation; unclear, punitive.)
- 'Everyone does this.' (Minimizing your experience.)
- 'Why can't you just...' (Blaming framing.)
Keep focused: specific pattern, specific feeling, specific ask.
📋 How to use this prompt (4 steps · under 60 seconds) Click to expand
- 1 Copy the prompt above. Click "Copy prompt". XML-structured prompt now on clipboard.
- 2 Open ChatGPT, Claude, or Gemini. One-click launch above. Recommended: Opus 4 for nuance..
-
3
Paste + fill placeholders. Replace
{curly braces}with your context. Specificity = quality. - 4 Run + iterate. Setup: 2 min to try. Output: 30-60 min preparation.
Common use cases
- Before any hard conversation (work, family, romantic)
- Conversations you've been avoiding for months
Best AI model for this
Opus 4 for nuance.
Pro tips
- Intent audit honest — are you seeking understanding or being-right?
- Own your contribution before talking. 'I also...'
- Sleep before conversation if possible.
Customization tips
- For parents-of-adult-child specifically: they may be grieving loss of parenting role. Acknowledge if appropriate.
- For in-laws: spouse alignment critical before conversation.
- For spouse-conversations: therapist setting sometimes better than solo.
Variants
Default Prep
General hard conversation
Work/Professional
Work-context specific
Family/Partner
Close-relationship specific
Frequently asked questions
Common questions about this prompt and how to get the best results from it.
How do I use the Hard Conversation Preparation Workbook prompt?
Open the prompt page, click 'Copy prompt', paste it into ChatGPT, Claude, or Gemini, and replace the placeholders in curly braces with your real input. The prompt is also launchable directly in each model with one click.
Which AI model works best with Hard Conversation Preparation Workbook?
Opus 4 for nuance.
Can I customize the Hard Conversation Preparation Workbook prompt for my use case?
Yes — every Promptolis Original is designed to be customized. Key levers: Intent audit honest — are you seeking understanding or being-right?; Own your contribution before talking. 'I also...'
What does it cost to use this prompt?
The prompt itself is free, MIT-licensed, with no email signup required. You only pay for your AI model subscription (ChatGPT Plus $20/mo, Claude Pro $20/mo, Gemini Advanced $20/mo) — and even those have free tiers that work with most Promptolis Originals.
How is this different from PromptBase or PromptHero?
PromptBase sells prompts in a marketplace ($2-15 each). PromptHero focuses on image-generation prompts. Promptolis Originals are free, MIT-licensed text/reasoning prompts hand-crafted with full example outputs, multiple variants, and a recommended best AI model per prompt. We don't sell anything.
Explore more Originals
Hand-crafted 2026-grade prompts that actually change how you work.
← All Promptolis Originals