Blog / The category
Can an AI actually run D&D 5e?
(updated )
Yes, for most of it - and the honest answer to this question is specific rather than enthusiastic, so here is the specific one. On Rolegend, 71 sections of D&D 5e are enforced in code. 23 more are partly enforced. 26 are not enforced at all and are left to the Game Master to adjudicate in prose. That breakdown is published rule by rule at /rules-coverage, and it was last checked against the code on 11 August 2026.
The rest of this is what those three numbers mean, because the split between them is not arbitrary. There is a clean line running through fifth edition, and almost everything on the far side of it fails for the same single reason.
What is genuinely solved
The bookkeeping half, which is the half most people assume is the hard part.
Dice, modifiers and advantage. Hit points and damage. Conditions. Spell slots. Short and long rests. Inventory and carried weight. Experience and leveling. On Rolegend these belong to Keystone Engine, which enforces the rules and is the only thing on the platform permitted to change a number. It runs on the server. It rolls before any narration exists. ROWAN narrates the world - it is handed the result and writes what happened, and it cannot ask for a different one.
Conditions are the example worth dwelling on, because they are the case where "the AI knows the rules" and "the software enforces the rules" come apart most visibly. A condition on Rolegend is a stored row, and the dice code reads it: saves that should auto-fail do auto-fail, an attacker who should have advantage gets it, a character who should be rolling at disadvantage rolls at disadvantage, and one who cannot act cannot act. Nobody has to remember. Nothing depends on the condition being mentioned in the last few hundred words of narration.
That is the general shape of the solved half. It is arithmetic over stored state - a database problem wearing a rulebook. The reason it goes wrong in a plain chat window is not that it is difficult; it is that nothing there is storing anything, so every value survives only as long as it keeps being repeated.
What is partly solved
Most of the Partly column is one boundary drawn in the same place each time: the battle map. Where the campaign author drew one, the geometry is enforced; where they did not, it is narrated.
Movement and distance. On a battle map the budget is real: every square is charged, difficult terrain costs double, Dash doubles it, and a move you cannot afford is refused rather than narrated. At a location with no map, distance is described and speed is advisory.
Cover. On a map, cover is traced from the walls, corner to corner: half cover adds 2 to the AC the server adjudicates against, three-quarters adds 5, and total cover refuses the attack outright. With no map it is a Game Master judgement.
Opportunity attacks. On a map, any move reports exactly which enemies it provokes, worked out from reach and the path taken, gated on the reaction and aware of Disengage. With no map the Game Master has to notice the trigger.
Flanking. On a map the server grants the advantage itself, as the Dungeon Master's Guide variant: a melee attack lands with advantage while a living ally stands on the opposite side or corner of the enemy's space. With no map, surrounding somebody stays narration.
Grapple and shove. The contest is an ordinary roll, and what the map adds is the part that matters: a grappled creature cannot move at all, and a shove resolves as a real push, clipped by walls, with the exact fall derived over a ledge.
Encumbrance. Carried weight against Strength is enforced and imposes disadvantage. The speed reductions are not: the movement budget does not read how much you are carrying.
What is not solved
Fog of war, lighting and vision. The grid knows where everybody is and reads it for flanking, cover and range, but nothing hides a room until you have seen it, and darkness is a thing the Game Master describes rather than a thing the map enforces. Separately, mounted and underwater combat are marked Not modelled, which is a stronger admission than Not enforced: neither ruleset is implemented, and both are reference only.
Why positioning was the hard half
Every rule in the Partly list is a geometry question dressed as a rules question, and text is a poor map.
A grid answers "how far" by subtraction. Prose has no coordinates. Write "I back away from the ogre and shoot" and you have described an action perfectly well without ever fixing a distance, because no reader needed one. But an opportunity attack is entirely a question about a distance: did you leave its reach? To enforce that, the software has to know where you were - as a number - before the sentence exists. To write the sentence, it only has to be plausible.
Cover is worse, because it needs three positions rather than one: the attacker, the target, and the thing in between, plus whether the line from the first to the second passes through the third. None of this can be derived from a paragraph, because the paragraph was never carrying that information.
The tempting move is to ask a language model to hold the battlefield anyway. It will happily do it. That is precisely the problem: it always answers. It will tell you the ogre is twenty feet away, fluently, and thirty feet away four turns later, with no event in between that moved anybody. A rule enforced inconsistently is worse for a player than a rule that is openly not enforced, because you cannot plan around it - and planning around it is the entire point of tactical combat.
Which is why the fix was not a smarter model but an actual map. On Rolegend, locations the campaign author mapped hold positions as coordinates in encounter state, and the geometry rules read them. The honest edge of that fix is that maps are preset only - authored in advance, never improvised mid-fight - so a battle in a location nobody mapped is still narrated, the hold-the-battlefield problem still applies there, and the coverage table says which is which rather than letting you find out during a boss fight.
The limit that is not a rules problem at all
Everything above is solvable in principle, and the battle map is the proof: drawing one moved movement, cover and opportunity attacks a column to the left together, because they were always one problem.
The other limit does not work like that.
A good human Game Master does something no coverage table can measure: they plant something in your second session that pays off in your twentieth. They notice that you keep mentioning your character's brother and quietly build an arc out of it. They throw away the dungeon they spent a week on because the party got interested in the innkeeper instead. The surprise in that is not improvisation - a language model improvises fluently. It is intention held across months, by someone who wants the payoff to land on you specifically.
Structured state gets you the mechanical version of this. Rolegend stores plot flags, locations, NPC relationships and a rolling recap, so the world stays consistent and things you did forty turns ago are still true. Consistency is not the same as intention. A world that never forgets is a real achievement and it is not the same thing as a storyteller who has been setting you up for a month.
So the honest framing is that an AI Game Master is not a lesser version of a great table. It is a different thing that is available at two in the morning, never cancels, and will run a fight by the actual rules without arguing.
Why publishing the gaps is unusual
It is not normal, in this category, to ship a page listing what your product does not do. An AI Game Master demos extremely well for ten minutes, and the incentive is to let the demo be the answer.
The reason for publishing it anyway is that hour forty is where these products are decided, and hour forty is exactly when an unenforced rule surfaces as a surprise. A reader who knows before they start that a fight in an unmapped location is narrated rather than measured can play around it. A reader who finds out mid-encounter concludes, correctly, that the numbers were never being kept.
So the table at /rules-coverage carries a status against each rule, a line describing exactly what happens today, and the date it was last checked. It is a worse advert and a better instrument.
So, can an AI run it?
It can roll every die honestly, keep every number, apply every condition, track your slots and your rests and your pack, and play a coherent world at any hour you like. It can even run a battle map where the campaign author drew one - but it will not surprise you the way the best human Game Master you ever played with did.
Which of those matters more depends entirely on whether the alternative you are comparing it to is a great table, or no game at all.