You asked
How do I play?
Abstained — no grounded answer; closest passages below counted as honest abstainAsked with: Dungeon Lordsbg-45315-en-1e
I looked through Dungeon Lords's rulebook and couldn't find a solid answer to that one — and I'd rather tell you so than guess at your table. Try asking it another way, or ask me about setup, turns, or how the game ends: those I know cold.
The closest rulebook passages are below — check them before ruling.
When everyone has placed all three orders, everyone turns their first card (the one on the left) face up. Beginning with the starting player, each player finds the place on the Central Board corresponding to the revealed order and places one of his or her Minion Figures on the first empty space (the
The rules given above are appropriate for introducing new players to the game. For your next game, you can play with the full rules. There are only a few differences: In your first game, the inaccessible orders for the first round of the First Year were chosen randomly. In the full game, you have a
The Progress Board needs to be where everyone can see it, but only one player needs to be able to reach it. The Ministry of Dungeons warns that playing the full game with beginners leads to immorality in the form of unpaid taxes due to lack of funds. In a two- or three-player game, take the remainin
» Setup: Flip the Progress Board back to the Building side. Put new Combat Cards in the Town. Discard the paladin from the First Year if he is still in on the Central Board. » In a 2-player game, move the non-player Evil Counter 2 spaces down the Evilometer. » Choose a new sta
Use a Minion Figure to indicate which dungeon tile the ad -venturers will be attacking. You must choose among the un -conquered tiles nearest the entrance. Distance is measured as though you were walking through the dungeon. In round 1, this means you must choose the tile at the entrance. In later r
🔧 debug — where this ruling came from
- outcome
- ABSTAINED — Abstained — no grounded answer; closest passages below
- warm abstain
-
- this ruling — W1 — generic warm abstain · receipt: none (generic)
- corpus profile
- live,vps
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 83 ms · ask 3452 ms · total 3537 ms
- single-flight (PR-5)
- queued 0 ms · generation 3537 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 12, "score": 0.048916, "snippet": "When everyone has placed all three orders, everyone turns their first card (the one on the left) face up. Beginning with the starting player, each player finds the place on the Central Board corresponding to the revealed order and places one of his or her Minion Figures on the first empty space (the", "headingPath": "Revealing Orders", "sharpsignalDocId": 514}, {"page": 22, "score": 0.046402, "snippet": "The rules given above are appropriate for introducing new players to the game. For your next game, you can play with the full rules. There are only a few differences: In your first game, the inaccessible orders for the first round of the First Year were chosen randomly. In the full game, you have a ", "headingPath": "Full Game · Choosing Initial Inaccessible Orders · Special Events · Recruiting as First Order", "sharpsignalDocId": 514}, {"page": 7, "score": 0.045591, "snippet": "The Progress Board needs to be where everyone can see it, but only one player needs to be able to reach it. The Ministry of Dungeons warns that playing the full game with beginners leads to immorality in the form of unpaid taxes due to lack of funds. In a two- or three-player game, take the remainin", "headingPath": "Progress Board (Building side up) · Non-Player Dungeon Boards · Central Board · Starting Player Token · Training Scenario", "sharpsignalDocId": 514}, {"page": 23, "score": 0.044733, "snippet": "\u0007 »\u0007 \u0007 Setup: Flip the Progress Board back to the Building side. Put new Combat Cards in the Town. Discard the paladin from the First Year if he is still in on the Central Board. \u0007 \u0007 \u0007 \u0007 \u0007 \u0007 »\u0007 \u0007 In a 2-player game, move the non-player Evil Counter 2 spaces down the Evilometer. »\u0007 \u0007 Choose a new sta", "headingPath": "Second Year · Scoring", "sharpsignalDocId": 514}, {"page": 18, "score": 0.043905, "snippet": "Use a Minion Figure to indicate which dungeon tile the ad -venturers will be attacking. You must choose among the un -conquered tiles nearest the entrance. Distance is measured as though you were walking through the dungeon. In round 1, this means you must choose the tile at the entrance. In later r", "headingPath": "Choosing a Dungeon Tile · Example: · Choosing Defense · Combat in Tunnels · Combat in Rooms", "sharpsignalDocId": 514}, {"page": 17, "score": 0.043124, "snippet": "Like Event Tiles, the Adventurer Tiles for spring, summer, and fall are revealed at the beginning of the previous round. In this phase, the adventurers are assigned to the players' dungeons. Each player will get one adventurer. Assign adventurers in order, beginning with the one on the left (with th", "headingPath": "Adventurers Phase · Assigning Adventurers to 2 Players", "sharpsignalDocId": 514}, {"page": 7, "score": 0.043009, "snippet": "So far, we have only covered combat in tunnels. But some dun -geon tiles can be rooms. There are 2 differences: ·\u0007 \u0007 You can send up to 2 monsters into battle (along with any number of ghosts). When it is time for them to attack, you choose the order in which they do so. ·\u0007 \u0007 You can use 1 trap, jus", "headingPath": "Combat in Rooms · Rules · First Game · Setup · Distant Lands Board · Dungeon Boards", "sharpsignalDocId": 514}, {"page": 23, "score": 0.030769, "snippet": "\u0007 Choose a starting player and set up the game according to the pictures on pages 7-9. ·\u0007 \u0007 Randomly choose 2 Special Event Cards, which remain unknown for now. ·\u0007 \u0007 Shuffle your own Orders Cards and draw 3 at random. Choose 2 to be your inaccessible orders. All players reveal these simultaneously. ", "headingPath": "Setup · · \u0007 \u0007 New Round Phase", "sharpsignalDocId": 514}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- []
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 514 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 514 boosted
- answered-before recall
-
no past answered ruling for this game matched closely enough
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
- debug row retained until
- Nov 15, 2026 09:22
retrieval — what the passage search returned
what this block IS: the PASSAGE SEARCH's own results — the same search that fills this page's closest-passages list — and NOT the passages the answerer read. Answering runs its OWN retrieval: a far wider candidate pool, re-ranked down to a final handful, plus floors this search never applies — the base rulebook, surviving errata corrections, and one slot per book on a multi-book read. Each of those armed only if THIS ask sent what it needs: the boost block names the ids it forwarded, and the scope line names the books it read. A document the answer CITES that no row here names is therefore EXPECTED, not a defect: two searches, two candidate pools, two orders. The answerer's own final rows are shown in their own block below, beside these and never mixed into them.
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. This ruling ran the THREE-ARM fuse (full-text + vector + the doc-priority boost arm, which carried the base rulebook and/or the errata corrections this query matched), whose arithmetic ceiling is 0.04918 — all three arms ranking the same chunk #1 (ceiling = arms/(k+1) at k=60). The measured healthy band 0.016–0.033 was measured on TWO-arm asks and does not bound this one: its high end is the two-arm ceiling, and a third arm has room above it. A chunk only one arm ranked highly lands near 0.016 (that one arm's #1 vote), so 0.03 here is an excellent hit, not a 3% match.
per-arm ranks (the rank each search arm gave a chunk): NOT DISCLOSED by the gateway. Fusion happens gateway-side and only the FUSED score crosses the wire, so rulesage cannot show them without a gateway change. The rank column below is the FUSED rank (position in the returned list), which is real.
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| fused rank | document | heading | page | fused RRF score | snippet chars |
|---|---|---|---|---|---|
| #1 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Revealing Orders | p.12 | 0.048916 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #2 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Full Game · Choosing Initial Inaccessible Orders · Special Events · Recruiting as First Order | p.22 | 0.046402 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #3 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Progress Board (Building side up) · Non-Player Dungeon Boards · Central Board · Starting Player Token · Training Scenario | p.7 | 0.045591 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #4 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Second Year · Scoring | p.23 | 0.044733 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #5 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Choosing a Dungeon Tile · Example: · Choosing Defense · Combat in Tunnels · Combat in Rooms | p.18 | 0.043905 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #6 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Adventurers Phase · Assigning Adventurers to 2 Players | p.17 | 0.043124 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #7 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Combat in Rooms · Rules · First Game · Setup · Distant Lands Board · Dungeon Boards | p.7 | 0.043009 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #8 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Setup · · New Round Phase | p.23 | 0.030769 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
what the answerer read — the passages it actually had in front of it
what this block IS: the passages the ANSWERING read put in front of the answerer, in the order it read them — the other half of the two reads described above, and the one that decides what the answer could possibly say. Each row names the book it came from and where in that book it sits, what it scored when the search arms were fused, which arm carried it there, and whether the re-ranker chose it or a floor guaranteed it a slot. A row here that no passage-search row names is EXPECTED: a far wider pool, re-ranked, with floors the passage search never applies.
candidate pool: the answering read scored 70 passages, out of a ceiling of 80 set gateway-side. Both figures are reported by the gateway for THIS ask — measurements of what actually happened, not constants read out of anyone's source and printed here on faith.
floors armed for this ask: the base rulebook — armed · surviving errata corrections — not armed · one slot per book on a multi-book read — not armed. Every floor is stated on every ask, armed or not, so a floor that did not apply here is never mistaken for one this app does not know about.
arms fused for this ask: vector + full-text + the doc-priority boost arm. Stated separately from the rows because an arm that ran and carried nothing is a different fact from an arm that never ran.
| read at | document | heading | page | fused rank | fused RRF score | carried by | how it got its slot |
|---|---|---|---|---|---|---|---|
| #1 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Revealing Orders | p.12 | #1 | 0.048916 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Combat | p.23 | #9 | 0.030478 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text | the re-ranker chose it |
| #3 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Paladin | p.17 | #10 | 0.027921 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text | the re-ranker chose it |
| #4 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Progress Board (Building side up) · Non-Player Dungeon Boards · Central Board · Starting Player Token · Training Scenario | p.7 | #3 | 0.045591 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #5 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | End of the Round | p.17 | #21 | 0.014493 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #6 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Setup · · New Round Phase | p.23 | #8 | 0.030769 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Full Game · Choosing Initial Inaccessible Orders · Special Events · Recruiting as First Order | p.22 | #2 | 0.046402 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Dungeon Lords — Rulebook (corpus doc 514) | Production and Orders Retrieval Phase · Production · Orders Retrieval · Example: | p.16 | #16 | 0.023555 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text | the re-ranker chose it |
chosen chunks — what the answer actually cited
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| # | document | heading | page | quote chars |
|---|
generation — timing and the path taken
- timing split
- retrieval 83 ms · first delta 3443 ms · total 3537 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 0 ms · retrieval 83 ms · ask 3452 ms · gateway work 3537 ms · total 3537 ms
- tokens in (the prompt the answerer read)
- 3135
- tokens out (what the answerer generated)
- 9
- tok/sec
- 200.0 tok/sec — 9 output tokens in 0.045 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 14s ago)
- stream path
- streamed — the gateway pushed at least one accumulated draft
- watchdog
- first-token watchdog: 30s per arming window (rulesage.table.first-token-watchdog-seconds), re-armed once by the passages frame — so the worst case before a reader falls back to polling is 60s. Whether it actually fired is a BROWSER-side decision that never reaches the server, so it is not recorded here. The stream path above is the server's half of that story: whether a delta was emitted at all.
- num_ctx · think posture
- both are the CHILD's settings, not rulesage's, and no ask reply carries them — an answer never states which context window or think posture produced it. The live-seat line above reads them from the running child instead, where the gateway can answer for itself; it describes the child NOW, not this ask.
disposition
- outcome
- ABSTAINED — Abstained — no grounded answer; closest passages below
- abstain rationale
-
I don't have enough information.
the answerer's own words, verbatim — hostile corpus/LLM text, rendered escaped
setup-shape — why the checklist band did or didn't render
- decision
- NOT_SETUP_SHAPED — no setup-shape pattern matched this question
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 445), so "no registered errata card matched" above could never have matched one
Errata scope: the gate above matched this ruling's own edition only. When an ask also reads an expansion, that expansion's own registered errata cards stay outside the match — a stated phase-1 limitation, not a failed lookup.