How do I balance a D&D encounter for my party?

Encounter XP has to be multiplied by a factor based on the number of creatures, then compared against your party's thresholds. Asking for the adjusted figure and the difficulty band explicitly makes the maths checkable rather than assumed.

Why do AI-generated encounters feel flat?

Usually because every creature is a stat block with no motive, so the encounter has only one verb. Giving each creature something it wants creates the possibility of negotiation, betrayal or retreat.

Which AI model is best for creating a D&D encounter?

All of them handle this; what changes is the packaging. This page shows the same prompt written for Claude, ChatGPT, Gemini. Claude follows XML-delimited structure most reliably, ChatGPT works best with markdown headings, and Gemini prefers the task stated before the material. The content of the prompt is identical in each.

Can I change this prompt for my own situation?

Yes, and you should. Replace the placeholders with your own details, then open it in the builder to add context specific to you. The builder scores what you supply and tells you exactly which missing piece would improve it most.

Why does this prompt include rules I did not ask for?

Because editing / rewriting tasks carry requirements that experienced practitioners apply automatically and rarely write down. The compiler adds them so the output does not fail on something obvious. Every added rule is listed on the how it works page.

AI prompt for creating a D&D encounter

This is a ready-made AI prompt for creating a D&D encounter, written for Claude and free to copy. Encounter design fails on maths and on assumption. Generated encounters are routinely mis-balanced for the party level, and they assume players will fight — which is the one thing a real table reliably does not do. The prompt below handles that: it is compiled as a editing / rewriting task, so it carries the structure and the constraints that kind of work needs.

The prompt

Written for Claude. Compiled as a editing / rewriting task — improving existing text without changing what it means.

<role>
You are a line editor who improves prose without flattening the author’s voice.
</role>

<context>
Party: {{party_size}} players at level {{level}}, classes {{classes}}. Setting: {{setting}}. What I want it to feel like: {{tone}}.
</context>

<task>
Design a D&D 5e encounter for my party.
</task>

<constraints>
- Balance to the stated party size and level. State the adjusted XP and difficulty band.
- Give at least two routes through it, including one that avoids combat.
- Every creature needs a motive, not just a stat block.
- Include what happens if the party flees or negotiates.
- Do not reproduce published stat blocks verbatim; describe original creatures.
- Preserve the author’s voice, argument, and factual claims. Change wording, not meaning.
- Do not add new facts, examples, or claims that are not in the original.
- After the edited version, list the three most significant changes and why you made them.
</constraints>

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

Now, design a D&D 5e encounter for my party.

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

What makes creating a D&D encounter hard to prompt for

Encounter design fails on maths and on assumption. Generated encounters are routinely mis-balanced for the party level, and they assume players will fight — which is the one thing a real table reliably does not do.

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 editing / rewriting task assumes but nobody writes down: Preserve the author’s voice, argument, and factual claims. Change wording, not meaning. Do not add new facts, examples, or claims that are not in the original. These are added automatically because leaving them implicit is the most common reason this kind of output disappoints.

What to replace

Placeholder	What to put there
{{party_size}}	Your party size.
{{level}}	Your level.
{{classes}}	Your classes.
{{setting}}	Your setting.
{{tone}}	Your tone.

Check the output before you use it

Verify the adjusted XP against the encounter-building tables for your party level.
Confirm the non-combat route is genuinely viable, not a token gesture.
Check there is a defined outcome if the party runs away.

The same prompt for other models

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

ChatGPT

## Role

You are a line editor who improves prose without flattening the author’s voice.

## Context

Party: {{party_size}} players at level {{level}}, classes {{classes}}. Setting: {{setting}}. What I want it to feel like: {{tone}}.

## Task

Design a D&D 5e encounter for my party.

## Constraints

- Balance to the stated party size and level. State the adjusted XP and difficulty band.
- Give at least two routes through it, including one that avoids combat.
- Every creature needs a motive, not just a stat block.
- Include what happens if the party flees or negotiates.
- Do not reproduce published stat blocks verbatim; describe original creatures.
- Preserve the author’s voice, argument, and factual claims. Change wording, not meaning.
- Do not add new facts, examples, or claims that are not in the original.
- After the edited version, list the three most significant changes and why you made them.

## Output format

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

Now, design a D&D 5e encounter for my party.

Gemini

**Task**

Design a D&D 5e encounter for my party.

**Role**

You are a line editor who improves prose without flattening the author’s voice.

**Context**

Party: {{party_size}} players at level {{level}}, classes {{classes}}. Setting: {{setting}}. What I want it to feel like: {{tone}}.

**Constraints**

- Balance to the stated party size and level. State the adjusted XP and difficulty band.
- Give at least two routes through it, including one that avoids combat.
- Every creature needs a motive, not just a stat block.
- Include what happens if the party flees or negotiates.
- Do not reproduce published stat blocks verbatim; describe original creatures.
- Preserve the author’s voice, argument, and factual claims. Change wording, not meaning.
- Do not add new facts, examples, or claims that are not in the original.
- After the edited version, list the three most significant changes and why you made them.

**Output format**

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

Now, design a D&D 5e encounter for my party.

Common questions

How do I balance a D&D encounter for my party?: Encounter XP has to be multiplied by a factor based on the number of creatures, then compared against your party's thresholds. Asking for the adjusted figure and the difficulty band explicitly makes the maths checkable rather than assumed.
Why do AI-generated encounters feel flat?: Usually because every creature is a stat block with no motive, so the encounter has only one verb. Giving each creature something it wants creates the possibility of negotiation, betrayal or retreat.
Which AI model is best for creating a D&D encounter?: All of them handle this; what changes is the packaging. This page shows the same prompt written for Claude, ChatGPT, Gemini. Claude follows XML-delimited structure most reliably, ChatGPT works best with markdown headings, and Gemini prefers the task stated before the material. The content of the prompt is identical in each.
Can I change this prompt for my own situation?: Yes, and you should. Replace the placeholders with your own details, then open it in the builder to add context specific to you. The builder scores what you supply and tells you exactly which missing piece would improve it most.
Why does this prompt include rules I did not ask for?: Because editing / rewriting tasks carry requirements that experienced practitioners apply automatically and rarely write down. The compiler adds them so the output does not fail on something obvious. Every added rule is listed on the how it works page.

Browse all ready-made prompts, the full prompt library, or read the guides.