How to judge an AI Game Master before you hand it a character
You have decided you want one. The hard part is telling them apart, because they all describe themselves in the same words. Here are five questions that separate them, a test for each, and our own answers.
The five questions that separate them
Every product in this category says it runs fifth edition, remembers your story and rolls real dice. Those claims are not lies; they are pitched where they cannot be wrong, which is a different problem. What differs is underneath:
- Who rolls the die, and when?
- Where does your character sheet live?
- What survives a month away?
- Are the rules enforced, or described?
- Is there a real map under the fight?
Each has a test you can run in an evening, usually on a free tier. Below is the question, the test, and our answer. Run them on whoever else is on your shortlist. If you want the category explained from the beginning first, that is a different page: what an AI Game Master is.
1. Who rolls the die, and when?
The "when" is the half that gets skipped, and the half that matters. If a language model produces the number, the number arrives after the sentence that needed it, which makes it a plot decision wearing a d20 costume. A deterministic roll happens before any narration exists, so the story is downstream of it and has to cope.
How to test it. Fail something you care about, then ask for a reroll, politely, twice. Suggest the DC seemed high. Where the result is a stored fact you get a refusal and the same total; where it is a sentence you will usually be offered a way out within two messages. Then look for the arithmetic: a real roll can show you the dice, your modifiers and the total, because it has them. A narrated one shows you a number and an adjective.
Ours. Rolegend runs on Keystone Engine, a game engine that sits apart from the AI and handles the dice and the game state. When your character has to roll, the game waits for you to press the die. Then the engine throws it, adds the modifiers off your sheet, and records the result before a word of the reply exists. ROWAN, our narrator, is handed that result and writes what happened. It cannot roll again or change a total. Every roll on screen shows its formula and its result, so you can check the sum yourself. ROWAN chooses the tone of a failure; it cannot turn a 4 into a 19.
2. Where does your character sheet live?
There are only two answers. Either your hit points, gold, conditions and inventory are data that something owns and updates, or they are sentences in a conversation a model has to keep re-reading. Identical in the first hour. Not at the fortieth turn.
How to test it. Pick up something small and unglamorous early, such as a crowbar or a length of rope, and never mention it again. Much later, ask what is in your pack. Take damage, take a short rest, and check the numbers against what you would work out on paper. And look at the interface: is your sheet a screen you can open, or only a thing you can ask about?
Ours. The sheet is rows in a database, not recall. Keystone keeps hit points, inventory, conditions, spell slots, rests and experience, and is the only thing permitted to change them. ROWAN reads that state and never writes to it. Nothing quietly stops existing because the conversation got long.
3. What survives a month away?
Continuity is the claim everybody makes and the one nearly nobody defines. Ask what exactly is preserved: a summary of the story so far, or the state of the world? A summary is lossy on purpose and gets lossier each time it is rewritten. A stored fact is either there or it is not.
How to test it. Stop mid-scene. Come back a fortnight later and, without reminding it of anything, ask where you are, who you owe, who owes you, and which threads are still open. Then ask about something specific from early on: a name, a bargain, a door you did not open.
Ours. Where you are, your plot flags, your standing with people you have met and your open threads are structured state, kept as facts rather than left to a model to remember. Every turn you have played is also searched by meaning, so when what you do now touches a scene from weeks ago, that exchange comes back to the Game Master in the words it first used. Anything canonical (a number, an item, a flag) is in the state.
4. Are the rules enforced, or described?
"Runs D&D 5e" can mean the software applies exhaustion, or that it can hold a conversation about exhaustion. Both fit the same marketing sentence, and the difference only shows up when a rule costs you something you did not want to pay.
How to test it. Pick three rules you care about (concentration, death saves, encumbrance, whatever you would notice) and try to break each on purpose. Cast a second concentration spell. Then ask the question that really sorts this category: ask the product where it stops. Something that enforces rules in code knows which ones it does not enforce and can list them. Something that narrates them cannot: the boundary exists nowhere except in the prose.
Ours. Most of the ruleset is enforced in code: dice and modifiers, hit points, conditions, spell slots, concentration, rests, inventory and leveling. The rules of position are enforced on the Virtual Tabletop. In a fight with no map, and for everything else, the Game Master narrates.
5. Is there a real map under the fight?
Fifth edition combat assumes a grid. Movement, cover, opportunity attacks, flanking and range are all questions about distance, and prose has no coordinates. A product either draws the fight and measures it, or describes it and hopes the description stays consistent.
How to test it. Start a fight and back away from something with a long reach. Ask whether that provoked an attack, then ask how far away it is now. Two turns later, ask again. On a real map the answer is a number of squares, and it changes only when somebody moves.
Ours. Rolegend's Virtual Tabletop puts a fight on a battle map, with a token for every hero and every enemy, and you drag yours to move. The map shows how far you can really go, and the engine enforces movement, difficult terrain, cover, line of sight, opportunity attacks, flanking, weapon ranges, light and fog of war. Fog of war follows what your character can really see, so enemies out of sight stay hidden. And the table is open to your friends: up to 6 players, each with their own character on the same map, playing live when everyone is online or async whenever they want.
The sixth question, for later
How do you get your writing out? Ask before you start, not after eighty thousand words are in somebody's database. Here, any campaign downloads as a transcript on every plan including the free one, and the account exports from Settings. Where it is a paid feature elsewhere, better to know on day one than on the day you leave.
What to do with this
Run the five tests. They work on a free tier and they beat any feature grid. Our own answers, and how we stand next to everyone else, are at /compare.
If they are the answers you wanted, the fastest way to test the dice is to go and fail a roll.
Questions
How is this different from playing D&D with ChatGPT?
In a chat window, the same thing that writes the story also writes the numbers. So a roll is whatever the sentence needed it to be, and asking again nicely tends to produce a better one.
Here those are two different systems. You roll your own die, andKeystone adds the modifiers from your sheet before any narration exists. ROWAN gets the result and has to live with it. Your character sheet works the same way: hit points, gold, conditions and quests are stored and updated, not held in a conversation that has to keep remembering them. Nothing quietly drops your shield forty turns in.
A chat window also only knows what still fits in it. Every turn you have played here is searched by meaning instead, so a detail from a session weeks ago is put back in front of ROWAN in the words you used. It does not survive only if a summary happened to keep it.
Can the AI Game Master cheat on a dice roll?
Not on the number. ROWAN never touches the dice. Keystone hands you the die, adds up your bonuses off your sheet, and records the result before a single word of the reply is written.
ROWAN chooses how a result reads, gently or hard, as the story needs. It cannot turn a 4 into a 19, and it cannot decide after the fact that the lock was easier than it said.
What happens if I do not play for a few weeks?
Nothing at all. There is no streak to break, no daily allowance and no session that expires. You end a session when you decide to, and ending one writes a recap ROWAN carries into the next. Come back in March and your hit points, your gold and your open quests are exactly where you left them.
Can I play Rolegend with friends?
Both. On the paid plan a host sends an invite link, and up to 6 players sit at one table, the host included. Friends on the free plan can join. Each player plays their own character and pays for their own turns. Friends who are online together play live, and the table is also async play-by-post, so each player can drop in whenever they want. In a fight each player acts on their character's turn, and an email says when the table waits for you.
Alone, one person does not mean one character. On the paid plan a run holds a party of up to 6: you play the ones you want to play and ROWAN runs the rest as companions. Keystone rolls their initiative, and each companion acts on its own turn. The free plan is a single character.
Which AI model does Rolegend use?
A large language model that we choose and configure, and which one is a setting rather than a feature. It can change between one turn and the next, and there is no per-player model picker. That is why no vendor is named anywhere on this page. A name we could switch tomorrow would be a promise we could not keep.
The companies that can receive what you write are named, with the date the list was last checked, on the sub-processors page.
It also matters less than you would think. Dice, damage, conditions and every other rule are resolved by Keystone, so changing the model cannot change how the game plays out, only how it reads.
Why play on Rolegend
- When your character acts, the game hands you the die to roll, and Keystone Engine adds the modifiers from your sheet.
- On the battle map, Keystone Engine enforces movement, difficult terrain, cover, line of sight, opportunity attacks, flanking and weapon ranges, and every player at the table moves on the same map.
Start
Take a ready-made character and write one line, alone or with friends.
Request early access