You asked
How do I play?
Abstained — no grounded answer; closest passages below counted as honest abstainAsked with: Caylusbg-18602-en-1e
I looked through Caylus'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.
N.B.: The same rules apply for 3, 4 or 5 player games. Adjustments for the 2 player game are explained at the end of this booklet. The board is placed at the center of the table. The brown, gray and blue building tiles are sorted out by color, and placed face up on the side of the board. The green t
The game ends right after the scoring of the Towers section (that is, after the bailiff has reached the Towers scoring space or when the 14 parts of the Towers have been built). The players add the following points to the points they have already gained during the game: 3 points per gold cube they h
Each player plays the part of a master builder and has a team of 6 workers, some resources and a little money (deniers). The workers can be placed either in the city or in the castle: At the beginning of the game, the city is nothing but a small village. Apart from special buildings (an inn, a joust
Each game of Caylus can evolve very differently. Depending on the players' choices (Which buildings should they build first? Will there be a lawyer? When will the mason arrive on the board?), the game will develop in different ways. Some games will see huge resources, others will not. Some games wil
The gate allows you to temporize, and pass later to hide your intentions.The trading post provides money at the best moment (that is, right before the provost moves). The guild is the most economical way to move the provost. The joust field allows you to take advantage of the King's favor without ha
🔧 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 89 ms · ask 2362 ms · total 2454 ms
- single-flight (PR-5)
- queued 0 ms · generation 2454 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.048916, "snippet": "N.B.: The same rules apply for 3, 4 or 5 player games. Adjustments for the 2 player game are explained at the end of this booklet. The board is placed at the center of the table. The brown, gray and blue building tiles are sorted out by color, and placed face up on the side of the board. The green t", "headingPath": "Setup · Resources: · Wood · Pawns:", "sharpsignalDocId": 310}, {"page": 8, "score": 0.047643, "snippet": "The game ends right after the scoring of the Towers section (that is, after the bailiff has reached the Towers scoring space or when the 14 parts of the Towers have been built). The players add the following points to the points they have already gained during the game: 3 points per gold cube they h", "headingPath": "End of the game · Caylus for 2 players", "sharpsignalDocId": 310}, {"page": 4, "score": 0.045285, "snippet": "Each player plays the part of a master builder and has a team of 6 workers, some resources and a little money (deniers). The workers can be placed either in the city or in the castle: At the beginning of the game, the city is nothing but a small village. Apart from special buildings (an inn, a joust", "headingPath": "Game principles · ● the city :", "sharpsignalDocId": 310}, {"page": 8, "score": 0.032258, "snippet": "Each game of Caylus can evolve very differently. Depending on the players' choices (Which buildings should they build first? Will there be a lawyer? When will the mason arrive on the board?), the game will develop in different ways. Some games will see huge resources, others will not. Some games wil", "headingPath": "Hints", "sharpsignalDocId": 310}, {"page": 8, "score": 0.031746, "snippet": "The gate allows you to temporize, and pass later to hide your intentions.The trading post provides money at the best moment (that is, right before the provost moves). The guild is the most economical way to move the provost. The joust field allows you to take advantage of the King's favor without ha", "headingPath": "Hints", "sharpsignalDocId": 310}, {"page": 5, "score": 0.030769, "snippet": "The player who places the worker gives the stock a sum of money that is equal to the smallest unoccupied number on the passing scale (between 1 and 5 deniers according to the number of players who have already passed). Then, the player places one of their workers on the opponent's building of their ", "headingPath": "c) placing a worker on one of another player's buildings · d) placing a worker on one of your own buildings · e) placing a worker in the castle · Phase 3 - Activating special buildings · a) the gate · b) the trading post · …", "sharpsignalDocId": 310}, {"page": 5, "score": 0.030303, "snippet": "Following the passing order of phase 2 (that is, the first player who passed speaks first), the players now have the opportunity to move the provost. The provost's final position will determine which buildings will be activated. Each player can move the provost 1 to 3 spaces forward or backward by p", "headingPath": "Phase 4 - The provost's move · Phase 5 - Activation of the buildings", "sharpsignalDocId": 310}, {"page": 4, "score": 0.029851, "snippet": "The player gives the stock a sum of money that is equal to the smallest unoccupied number on the passing scale (between 1 and 5 deniers according to the number of players who have al -ready passed). Then, the player places one of their workers on the space of a special, neutral or fixed building of ", "headingPath": "b) placing of a worker on a special, neutral or fixed building", "sharpsignalDocId": 310}]
- 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 310 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 310 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 13, 2026 20:47
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 Caylus — Rulebook (corpus doc 310) | Setup · Resources: · Wood · Pawns: | p.3 | 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 Caylus — Rulebook (corpus doc 310) | End of the game · Caylus for 2 players | p.8 | 0.047643 (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 Caylus — Rulebook (corpus doc 310) | Game principles · ● the city : | p.4 | 0.045285 (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 Caylus — Rulebook (corpus doc 310) | Hints | p.8 | 0.032258 (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 Caylus — Rulebook (corpus doc 310) | Hints | p.8 | 0.031746 (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 Caylus — Rulebook (corpus doc 310) | c) placing a worker on one of another player's buildings · d) placing a worker on one of your own buildings · e) placing a worker in the castle · Phase 3 - Activating special buildings · a) the gate · b) the trading post · … | p.5 | 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 |
| #7 | RULEBOOK Caylus — Rulebook (corpus doc 310) | Phase 4 - The provost's move · Phase 5 - Activation of the buildings | p.5 | 0.030303 (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 Caylus — Rulebook (corpus doc 310) | b) placing of a worker on a special, neutral or fixed building | p.4 | 0.029851 (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 24 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 Caylus — Rulebook (corpus doc 310) | Setup · Resources: · Wood · Pawns: | p.3 | #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 Caylus — Rulebook (corpus doc 310) | Game principles · ● the city : | p.4 | #3 | 0.045285 (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 |
| #3 | RULEBOOK Caylus — Rulebook (corpus doc 310) | b) placing of a worker on a special, neutral or fixed building | p.4 | #8 | 0.029851 (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 |
| #4 | RULEBOOK Caylus — Rulebook (corpus doc 310) | These allow you to build new buildings on the board: | p.6 | #12 | 0.014286 (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 |
| #5 | RULEBOOK Caylus — Rulebook (corpus doc 310) | c) the lawyer | p.6 | #14 | 0.013514 (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 Caylus — Rulebook (corpus doc 310) | Scoring : · Towers : | p.7 | #11 | 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 |
| #7 | RULEBOOK Caylus — Rulebook (corpus doc 310) | c) placing a worker on one of another player's buildings · d) placing a worker on one of your own buildings · e) placing a worker in the castle · Phase 3 - Activating special buildings · a) the gate · b) the trading post · … | p.5 | #6 | 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 |
| #8 | RULEBOOK Caylus — Rulebook (corpus doc 310) | End of the game · Caylus for 2 players | p.8 | #2 | 0.047643 (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 |
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 89 ms · first delta 2355 ms · total 2454 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 89 ms · ask 2362 ms · gateway work 2454 ms · total 2454 ms
- tokens in (the prompt the answerer read)
- 3559
- 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 28s 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 238), 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.