How It Works Primer Tools Pricing About FAQ Blog Contact Sign in Sign Up
← All posts

Running D&D in ChatGPT: What Works and Where It Breaks

The short answer

ChatGPT can run a genuinely fun D&D session if you set it up well: a DM role prompt, a session zero, and explicit rules for dice and turns. It breaks in predictable places, because every piece of game state lives in the context window. HP drifts, inventory duplicates, dead NPCs return, and the campaign quietly resets as the conversation grows. This guide covers the setup that works, the exact failure points, a five-prompt memory test you can run yourself, and when a purpose-built AI DM is the better tool.

More people try to run D&D in ChatGPT than in any purpose-built tool, and most of them have a great first session. This is the honest guide to doing it well: the setup that works, the failure points that end campaigns, and how to tell when you have outgrown it. We make a purpose-built AI dungeon master ourselves, so read the recommendations knowing that, but the setup advice below is the same advice we would give a friend.

The setup that actually works

ChatGPT defaults to being an agreeable assistant, which makes a terrible DM. The fix is a role prompt that gives it a spine. Structure it in three parts: the job, the rules of engagement, and the state it must track.

A working session zero prompt looks like this:

You are a D&D 5e dungeon master. Run a campaign for one player.

Rules of engagement:
- Never decide my character's actions or dialogue.
- Ask for a roll before narrating any uncertain outcome, and state the DC first.
- NPCs have their own goals and can refuse, lie, or fight.
- Failure is allowed. Do not soften consequences.

Track after every scene, in a block at the end of your reply:
HP, spell slots, inventory changes, gold, active quests, and NPCs met.

Start with session zero: ask me five questions about my character
and the kind of campaign I want, then open scene one.

Two details in that prompt do most of the work. Stating the DC before the roll stops retroactive difficulty, and the end-of-scene state block gives you something to paste back in when the conversation resets.

For combat, ask it to run initiative explicitly: list combatants in order, resolve one turn at a time, and show enemy HP as descriptions (bloodied, staggering) rather than numbers if you want tension. Roll your own dice physically or with a dice app, and report the result. ChatGPT will happily generate a "roll" for you, but a number it writes is a narrative choice, not a random outcome.

For state, the workarounds are manual but effective for a while: re-paste your character sheet at the start of each session, end each session with "give me a structured recap of everything that changed," and keep the recap file yourself. Custom instructions or a Project can hold your standing rules so you only re-paste state, not setup.

Where it breaks, precisely

Every one of these failures comes from the same root cause, so it is worth stating plainly. ChatGPT stores your campaign in the context window, not in a game state. There is no character sheet object, no dice ledger, no quest database. There is a rolling transcript, and when the transcript outgrows the window, the oldest facts silently stop existing.

The practical symptoms arrive in a predictable order:

Memory features, Projects, and summaries delay all of this. They do not change its nature, because they store prose summaries rather than structured state. A summary that says "the party is wounded" does not know your cleric has 7 HP.

Run the five-prompt memory test

You do not have to take our word for where the line is. The five-prompt AI DM memory test is designed exactly for this: it checks delayed recall, item consumption, character death continuity, quest consequences, and whether the system stops an illegal action, in five prompts you can paste into any tool. Run it against your ChatGPT campaign at session three and you will find the drift before it finds you.

When to switch to a purpose-built tool

Switch when you catch yourself doing the bookkeeping you wanted a DM to do: re-pasting sheets, arguing about what the transcript said, or re-rolling "impossible" successes. That is not a prompting failure on your part. It is the architecture.

A purpose-built tool splits the jobs. The game engine runs the game, and the AI DM narrates on top of it. In TableForge, dice, HP, spell slots, conditions, and combat resolve in deterministic code, campaign state persists across sessions, and play works solo, with one friend, or with a group up to six. The full architectural comparison is in AI dungeon master vs ChatGPT, and the named comparison of ten AI dungeon masters covers the rest of the field.

If you prefer Claude's prose, everything in this guide applies there too, and we wrote the same honest assessment in Claude as a dungeon master. If you would rather build the stack yourself, running your own AI DM covers what that takes.

ChatGPT is a genuinely good narrator and a fine way to discover that you enjoy this kind of play. Enjoy the one-shots. When you want the campaign to hold together, use a tool that keeps the game outside the conversation.

Frequently asked questions

Can ChatGPT be a dungeon master?
Yes, for one-shots and casual play. With a good role prompt, ChatGPT narrates well, improvises NPCs, and keeps a short adventure moving. It has no rules engine, no real dice, and no game state outside the conversation, so long campaigns drift: HP and inventory desynchronize, and rulings contradict earlier sessions. Treat it as a talented narrator you must referee, not a complete game.
Why does ChatGPT forget my campaign?
Because the campaign only exists in the conversation's context window. When the conversation grows past that window, the oldest text is no longer visible to the model, so early NPCs, promises, and items effectively stop existing. Memory features and summaries slow this down but store prose, not structured game state, so numbers like HP and spell slots still drift.
How do I make ChatGPT remember my D&D game?
Keep a canonical state block (character sheet, HP, inventory, active quests) and re-paste it at the start of every session. End each session by asking for a structured recap and save it yourself. Use Projects or custom instructions for standing rules. These workarounds help, but you are the save file: nothing updates automatically, and anything you do not restate will eventually fall out of context.

Keep reading